INDEX
Explanations
mentions of historical events and political movements
New Auto-Interp
Negative Logits
van
-0.18
meisje
-0.17
Dit
-0.16
oir
-0.15
.setViewport
-0.15
vom
-0.15
angs
-0.14
forum
-0.14
Dat
-0.14
lation
-0.14
POSITIVE LOGITS
rol
0.18
peri
0.16
zenÃŃ
0.16
Ñĥда
0.15
zen
0.15
idable
0.15
ICODE
0.15
kte
0.15
cav
0.15
plane
0.14
Activations Density 0.080%