INDEX
Explanations
references to political initiatives or electoral processes
New Auto-Interp
Negative Logits
alu
-0.18
Loot
-0.16
anki
-0.15
iyan
-0.15
ulla
-0.15
agi
-0.15
IPH
-0.14
Pixel
-0.14
pawn
-0.14
Ñĸли
-0.14
POSITIVE LOGITS
ulator
0.16
RPC
0.15
oyal
0.14
fy
0.14
erts
0.14
uncont
0.14
eper
0.14
upiter
0.13
uer
0.13
776
0.13
Activations Density 0.041%