INDEX
Explanations
references to domestic issues and policies
New Auto-Interp
Negative Logits
ventus
-0.15
еÑı
-0.14
idor
-0.14
sburg
-0.14
upy
-0.14
nder
-0.14
çĬ
-0.14
oined
-0.14
ven
-0.14
apers
-0.13
POSITIVE LOGITS
ized
0.17
/local
0.16
izando
0.15
Affairs
0.15
/private
0.15
izes
0.14
ated
0.14
ize
0.14
ieux
0.14
age
0.14
Activations Density 0.012%