INDEX
Explanations
governmental titles and positions related to politics
New Auto-Interp
Negative Logits
PÅĻÃŃ
-0.17
gnu
-0.16
eurs
-0.15
VIC
-0.15
@nate
-0.15
UpInside
-0.14
OMPI
-0.14
ACHINE
-0.14
DMIN
-0.14
achine
-0.14
POSITIVE LOGITS
ittest
0.18
ibbon
0.17
Nat
0.16
ittel
0.15
027
0.14
eteor
0.14
iju
0.14
etik
0.14
Nat
0.14
hepat
0.13
Activations Density 0.068%