1
Your word
measured
“make love, not war”
Definitions come from WordNet, a hand-curated dictionary.
engage in
hacer is Spanish for made, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Spanish headword, not a Spanish definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“make love, not war”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits hacer itself, not made — a tokenizer does not care what language it is fed. It is the only panel here that does.
This is the tokenizer splitting text, not the model understanding it.
break is the dictionary opposite of made, yet this model puts it closer than 26 of the 41 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to made, 1 of 8 also appear in the dictionary. 41 of 67 dictionary synonyms are in this build; the rest have no vector to compare yet.
break is the dictionary opposite of made, yet this model puts it closer than 32 of the 41 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to made, 1 of 8 also appear in the dictionary. 41 of 67 dictionary synonyms are in this build; the rest have no vector to compare yet.
break is the dictionary opposite of made, yet this model puts it closer than 23 of the 41 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to made, 1 of 8 also appear in the dictionary. 41 of 67 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.
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 made. 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 made. 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 made. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.