INDEX
Explanations
references to political parties and affiliations
New Auto-Interp
Negative Logits
httphttps
-0.91
OGND
-0.81
resourceCulture
-0.58
jadx
-0.56
principalColumn
-0.54
isInitialized
-0.54
\{\\-0.54
aarrggbb
-0.53
Personensuche
-0.53
Wikimedijinoj
-0.51
POSITIVE LOGITS
forces
0.78
controlled
0.55
Forces
0.52
controlled
0.52
bloc
0.48
leaders
0.47
camp
0.47
sympathi
0.46
leader
0.45
dominated
0.45
Activations Density 0.640%