1
Your word
measured
“his assassins were hunted down like animals”
Definitions come from WordNet, a hand-curated dictionary.
a murderer (especially one who kills a prominent political figure) who kills by a surprise attack and often is hired to do the deed
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“his assassins were hunted down like animals”
Definitions come from WordNet, a hand-curated dictionary.
This is the tokenizer splitting text, not the model understanding it.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Shade shows how close the model puts each word to bravo. 1 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Shade shows how close the model puts each word to bravo. 1 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Shade shows how close the model puts each word to bravo. 1 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.
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.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to bravo. That gap is the model’s own learned association.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to bravo. That gap is the model’s own learned association.
This model splits bravo into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to bravo. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.