INDEX
Explanations
instances of disagreement or objection in discussions
New Auto-Interp
Negative Logits
tin
-0.16
ustos
-0.16
tat
-0.15
.appspot
-0.15
chwitz
-0.14
عÙĬ
-0.13
tant
-0.13
té
-0.13
antro
-0.13
oday
-0.13
POSITIVE LOGITS
onym
0.14
Fry
0.13
ÑĮ
0.13
или
0.13
.ali
0.13
Schneider
0.12
OnError
0.12
Clr
0.12
ios
0.12
ès
0.12
Activations Density 0.115%