User Map - AI Fiction in the Wild

You’re looking at a map of ~1,830 estimated users who wrote 5+ fiction-related conversations in the WildChat dataset. IPs are bundled into estimated users via the shared-cluster method—two IPs in the same state that share a near-duplicate prompt cluster are treated as the same user. Each dot is then placed by the average embedding of that user’s fiction prompts; dot size shows how many conversations they had.

Fiction conversations Users

User Embedding Explorer

What am I looking at?

Each dot is one of ~1,830 estimated users who wrote 5 or more fiction-related conversations in the WildChat dataset. Users with similar fiction prompts appear close together.

Each user's position is the mean embedding of all their fiction prompts.

Topic labels come from GPT-4o.

Dot size reflects conversation count. Colors show majority category (>50% of conversations). Click a category to toggle; double-click to isolate. Click a topic to isolate it.

Learn more →