1
Your word
measured
“he was beginning to doubt the accuracy of his compass”
Definitions come from WordNet, a hand-curated dictionary.
the quality of being near to the true value
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“he was beginning to doubt the accuracy of his compass”
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 accuracy.
Shade shows how close the model puts each word to accuracy.
Shade shows how close the model puts each word to accuracy.
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 accuracy. 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 accuracy. 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 accuracy. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.