INDEX
Explanations
references to Indian Prime Minister Narendra Modi
mentions of the name "Narendra Modi."
New Auto-Interp
Negative Logits
erie
-0.80
hops
-0.72
captcha
-0.72
Wonderland
-0.68
orbs
-0.67
gasp
-0.67
Wonders
-0.66
icle
-0.66
eyebrow
-0.65
arella
-0.64
POSITIVE LOGITS
Modi
1.00
Hussein
0.97
lihood
0.81
Tayyip
0.80
Kumar
0.80
Singh
0.78
sson
0.78
ammad
0.76
Sunder
0.74
WAYS
0.71
Activations Density 0.041%