Definitions come from WordNet, a hand-curated dictionary.
an alloy of iron with small amounts of carbon; widely used in construction; mechanical properties can be varied over a wide range
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to steel.
Shade shows how close the model puts each word to steel.
Shade shows how close the model puts each word to steel.
Model neighbours are distributional, not dictionary synonyms. Two words can be close because they appear in similar sentences, which is why an antonym can outscore a synonym here.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to steel. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to steel. That gap is the model’s own learned association.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to steel. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.