INDEX
Explanations
mentions of nationality, specifically Pakistani
references to Pakistani individuals or entities
New Auto-Interp
Negative Logits
aunder
-0.96
umbnails
-0.91
mble
-0.91
paio
-0.88
phasis
-0.79
ipel
-0.78
ascript
-0.77
llan
-0.76
win
-0.74
uers
-0.72
POSITIVE LOGITS
istani
1.43
Taliban
0.92
Pakistani
0.89
nationals
0.89
consulate
0.75
Pakistan
0.75
Pakistan
0.75
proverb
0.74
sensit
0.73
origin
0.73
Activations Density 0.008%