INDEX
Explanations
phrases related to religious or moral teachings
New Auto-Interp
Negative Logits
enheim
-0.17
мена
-0.17
736
-0.16
icter
-0.15
Fer
-0.15
lus
-0.15
dig
-0.15
umbledore
-0.14
.MixedReality
-0.14
धर
-0.14
POSITIVE LOGITS
omit
0.16
afx
0.15
Lindsay
0.15
Sink
0.15
ÙħاÙĦ
0.15
Warfare
0.14
omal
0.14
vn
0.14
kart
0.14
cos
0.14
Activations Density 0.099%