INDEX
Explanations
mentions of the name "Kore."
New Auto-Interp
Negative Logits
ftime
-0.85
ured
-0.78
issance
-0.73
gown
-0.66
handshake
-0.66
uation
-0.66
grooming
-0.65
urers
-0.64
obbies
-0.63
uated
-0.63
POSITIVE LOGITS
atown
1.34
tz
0.95
mallow
0.84
ano
0.84
Kore
0.83
geist
0.81
ç¥ŀ
0.79
anos
0.79
gon
0.79
amen
0.78
Activations Density 0.006%