INDEX
Explanations
mentions of the name "Kim."
New Auto-Interp
Negative Logits
iffin
-0.18
Millet
-0.17
ful
-0.16
GIN
-0.16
oplan
-0.15
mann
-0.15
sing
-0.15
377
-0.14
ucci
-0.14
reservations
-0.14
POSITIVE LOGITS
med
0.16
éĢģæĸĻçĦ¡æĸĻ
0.15
ung
0.15
adulti
0.14
rray
0.14
.desktop
0.14
hlas
0.14
ãģ£ãģ¨
0.14
uetype
0.14
áze
0.13
Activations Density 0.010%