INDEX
Explanations
references to "Lady Gaga"
references to the character "Lady" in the text
New Auto-Interp
Negative Logits
CAST
-0.82
Palestin
-0.72
constitu
-0.72
ADRA
-0.69
66666666
-0.69
emp
-0.65
srf
-0.65
insula
-0.64
aeda
-0.64
obyl
-0.63
POSITIVE LOGITS
Gaga
1.30
bug
1.18
bird
1.11
bugs
0.97
hawk
0.93
maid
0.89
birds
0.89
ng
0.86
weed
0.83
Lady
0.81
Activations Density 0.015%