INDEX
Explanations
expressions of disagreement or differing opinions
expressing disagreement
New Auto-Interp
Negative Logits
})*/
-0.47
});*/
-0.42
pool
-0.42
-0.40
}*/
-0.40
);*/
-0.37
ویکیپدی
-0.37
ventes
-0.36
publicités
-0.36
photos
-0.36
POSITIVE LOGITS
disagree
0.98
disagreed
0.96
disagrees
0.87
Disagree
0.84
Disagree
0.81
disagreement
0.79
disagreements
0.67
opinion
0.56
pendapat
0.55
mergeFrom
0.55
Activations Density 0.037%