INDEX
Explanations
content related to political finance and corruption
New Auto-Interp
Negative Logits
ãĥ¶
-0.16
'gc
-0.16
assic
-0.15
ToF
-0.15
ycin
-0.15
variants
-0.15
bia
-0.15
Ñģел
-0.15
/testify
-0.14
виÑĤ
-0.14
POSITIVE LOGITS
anzi
0.16
sert
0.16
Lomb
0.15
Garrison
0.15
GY
0.14
bery
0.14
iegel
0.14
oples
0.14
144
0.14
67
0.14
Activations Density 0.281%