INDEX
Explanations
mentions of the name "Kim."
New Auto-Interp
Negative Logits
znik
-0.15
oppins
-0.15
weg
-0.15
ignal
-0.15
اباÙĨ
-0.14
isseur
-0.14
gger
-0.14
orget
-0.14
rops
-0.14
ging
-0.14
POSITIVE LOGITS
ball
0.33
ber
0.30
Kardashian
0.29
pton
0.29
ura
0.28
yasal
0.28
my
0.27
Jong
0.26
iko
0.26
chi
0.26
Activations Density 0.004%