INDEX
Explanations
elements related to legislative processes and political articles
New Auto-Interp
Negative Logits
onia
-0.18
æĪ
-0.15
fur
-0.15
utations
-0.14
utton
-0.14
elling
-0.14
onder
-0.14
.shtml
-0.14
repreh
-0.14
uario
-0.13
POSITIVE LOGITS
oÅĻ
0.18
ůr
0.15
obs
0.14
rat
0.14
acyj
0.14
igne
0.14
Rat
0.14
.destroy
0.14
_CONTINUE
0.14
Rog
0.14
Activations Density 0.016%