You’re looking at a map of ~195,000 fiction-related ChatGPT conversations from the WildChat dataset. Each dot is one conversation; conversations with similar prompts sit close together. Hover or click a dot to peek at the prompt, search by keyword, or switch to viewing whole users.
Embedding Explorer
What am I looking at?

Each dot is one of ~195,000 fiction-related ChatGPT conversations from the WildChat dataset. Conversations with similar content appear close together.

Each conversation's first user message was embedded with all-MiniLM-L6-v2.

Topic labels come from GPT-4o from a sample of 20 representative prompts.

Learn more →

Loading sample...
Click to pin & view details