Click two words on the map. Closer dots are a stand-in for similar meaning — the same idea behind search, RAG, and recommendations.
Click two words. Distance on this map is a teaching stand-in for how embedding models place similar meanings near each other. It is not a real OpenAI or Voyage vector.
Word A
king
Word B
queen
Map distance
10.8
Very close — these ideas sit in the same neighborhood. Same-color dots are a cluster we placed by hand so the idea is visible.
Meaning as coordinates
An embedding is a list of numbers that places a word or sentence in a space. Nearby points tend to share meaning.
Search without keywords
“refund after two weeks” can still match a note titled “returns” if they sit near each other in that space.
This map is a sketch
Real models use hundreds or thousands of dimensions. Two dimensions are just so you can see clusters with your eyes.
No. Positions were placed by hand so royalty, cities, animals, and AI jargon form visible clusters. A production embedding model would compute the coordinates from data.
Even 3D is still a cartoon of a 768- or 3072-dimensional space. Two dimensions is enough to feel “near vs far.”
No. The map is static and runs only in your browser.
Tokenizer Playground
Type anything and watch it split into tokens live — the units LLMs actually read and get billed for.
Context Window Visualizer
See how much of a model's context window your text fills up, and what happens when you run out of room.
FROG in a Bowl Prompt Builder
Fill in Format, Role, Objective, Goal, and Context — get a copy-ready structured prompt in seconds.
Machine Learning Types
Three tiny games show what supervised, unsupervised, and reinforcement learning actually mean.
Neural Network Playground
Drag two sliders and watch a real, tiny neural network turn them into a decision, live.
Generative AI Playground
Watch AI write one word at a time by predicting what's most likely to come next.
RAG Playground
Ask a question, watch notes get retrieved, then see a grounded answer versus a hallucination.
Attention Visualizer
Click a word and see which others a toy transformer looks at — including the classic “it” puzzle.
Prompt Injection Lab
Watch a pasted email try to override a support agent, then flip a switch that treats it as data.
