1
Your word
measured
“weigh the good against the bad”
Definitions come from WordNet, a hand-curated dictionary.
that which is pleasing or valuable or useful
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“weigh the good against the bad”
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 goodness, 1 of 8 also appear in the dictionary.
Shade shows how close the model puts each word to goodness.
Shade shows how close the model puts each word to goodness.
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 goodness. 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 goodness. 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 goodness. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.