INDEX
Explanations
elements related to conflict and tension in social or political contexts
New Auto-Interp
Negative Logits
Bubble
-0.17
UBE
-0.16
seedu
-0.15
Hüs
-0.14
Bubble
-0.14
енка
-0.14
bote
-0.14
frared
-0.14
.Physics
-0.14
atural
-0.13
POSITIVE LOGITS
proverb
0.17
oppins
0.17
uis
0.15
oose
0.15
iod
0.14
ht
0.14
Os
0.14
Os
0.14
nda
0.14
enti
0.14
Activations Density 0.655%