1
Your word
measured
“brass is an alloy of zinc and copper”
Definitions come from WordNet, a hand-curated dictionary.
a mixture containing two or more metallic elements or metallic and nonmetallic elements usually fused together or dissolving into each other when molten
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“brass is an alloy of zinc and copper”
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 alloy. 2 of 3 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to alloy, 1 of 8 also appear in the dictionary. 2 of 3 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits alloy 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 alloy. 2 of 3 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 alloy 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.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to alloy. 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 alloy. That gap is the model’s own learned association.
This model splits alloy 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 alloy. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.