INDEX
Explanations
mentions of the name "Kohli" in various contexts
New Auto-Interp
Negative Logits
ech
-0.16
ialis
-0.16
iev
-0.15
eva
-0.15
isclosed
-0.15
ziel
-0.15
etten
-0.15
ÑĢап
-0.14
eya
-0.14
mÃŃt
-0.14
POSITIVE LOGITS
ler
0.20
istani
0.19
awks
0.17
esion
0.17
orta
0.17
ino
0.16
orte
0.16
anim
0.16
i
0.16
çIJ´
0.16
Activations Density 0.009%