Skip to content
ChatGPTDetect
English

How to tell if ChatGPT wrote it

Look for a cluster, not a single sign: stock phrases such as "the importance of" and "is essential", more em dashes than people usually write, neat lists of three, and sentences of very even length. Humans use all of these too, so a cluster is a reason to check, not proof. The figures below come from Fileverity's proprietary corpus of fully AI-written English from the OpenAI family compared with human writing.

Phrases that ChatGPT-family text uses more than people

Multipliers show how much more often a phrase appeared in AI-written text than in human writing.

Phrases that set ChatGPT apart from other AI families

Compared with other AI models, ChatGPT-family text leaned toward "intended to" (4.2 times), "useful" (4.8 times), "and whether" (4.9 times), "affect" (3.4 times), "try to" (3.3 times), "easier to" (3.1 times) and "can help" (3 times).

Structural markers

More of these than human writers:

Less of these than human writers:

Why phrases are not proof

Humans use every phrase and mark above, especially trained writers and anyone who has read a lot of formal prose. A student who writes "the importance of" is not a chatbot. Style is a signal, and editing, paraphrasing or a prompt that asks for a casual voice can remove many of these tells. Read the whole text, not the list.

What a detector reads that a list cannot

Veread reads patterns across whole passages, not isolated phrases. It marks the passages that carry the AI signal and shows writing-style similarity to ChatGPT and other families. In tests it wrongly flagged 0.5% of human-written text across seven languages and caught 98.3% of fully AI-written texts; the accuracy figures explain both. If you are reviewing student work, read AI detection for teachers.

Check a text now

Paste at least 100 words into the ChatGPT detector and see the verdict, the marked passages and the style similarity.

To compare all seven model families, see the guide on how each AI model writes.

Questions and answers

What are the signs ChatGPT wrote a text?

Common signs are phrases such as "importance of", "is essential" and "ensuring that", many em dashes, tidy three-item lists, evenly sized sentences and few parentheses, ellipses and exclamation marks. Each sign is a tendency, not proof.

Are em dashes proof of ChatGPT?

No. In fully AI-written English from the OpenAI family, em dashes appeared about 8 times as often as in human writing, but human writers use them too. Treat them as one signal among many.

Can humans write like this?

Yes. Every phrase below appears in human writing. The multipliers describe averages across many documents, not a single text.

Is a phrase list enough to detect ChatGPT?

No. A model such as Veread reads far more than phrase lists, and its result is a writing-style similarity, not proof. Try it in the ChatGPT detector.