INDEX
Explanations
phrases or words related to the Israel-Palestine conflict
references to Palestine
New Auto-Interp
Negative Logits
Dogs
-0.68
Camp
-0.66
cages
-0.65
Users
-0.64
Wolves
-0.64
Seat
-0.63
Plat
-0.62
ython
-0.61
utterstock
-0.61
OTOS
-0.60
POSITIVE LOGITS
este
3.89
estine
3.09
estate
1.09
erity
1.04
ogle
1.02
reme
0.98
mbudsman
0.95
ento
0.95
estro
0.92
emo
0.92
Activations Density 0.042%