INDEX
Explanations
references to the Bharatiya Janata Party (BJP)
New Auto-Interp
Negative Logits
opsis
-0.17
gew
-0.15
sdk
-0.14
unsupported
-0.14
Synd
-0.14
aub
-0.14
esson
-0.14
/Table
-0.14
lux
-0.13
ково
-0.13
POSITIVE LOGITS
Ĥ
0.17
749
0.15
ulling
0.15
Kem
0.14
ÑĥÑģ
0.14
़र
0.14
ģn
0.14
elez
0.14
дог
0.14
Blink
0.13
Activations Density 0.002%