INDEX
Explanations
instances of significant emotional expressions or sentiments
New Auto-Interp
Negative Logits
orgia
-0.17
339
-0.17
-
-0.16
arming
-0.16
Columbia
-0.15
RTL
-0.14
-0.14
con
-0.14
.
-0.14
together
-0.14
POSITIVE LOGITS
\OptionsResolver
0.16
iglia
0.15
hsi
0.14
мов
0.14
太éĥİ
0.14
kip
0.14
cased
0.14
.pub
0.14
nodoc
0.13
DISCLAIM
0.13
Activations Density 0.464%