INDEX
Explanations
references to political parties and electoral processes
New Auto-Interp
Negative Logits
íĨłíĨł
-0.16
icer
-0.16
eyin
-0.15
812
-0.14
pin
-0.14
orian
-0.14
uhn
-0.14
ponto
-0.14
åĵ
-0.14
ares
-0.13
POSITIVE LOGITS
ulator
0.17
slate
0.17
platforms
0.16
Running
0.16
ulators
0.15
ewise
0.15
RPC
0.15
crowded
0.15
bye
0.15
candidates
0.15
Activations Density 0.044%