INDEX
Explanations
mentions of candidates or politicians in parentheses
New Auto-Interp
Negative Logits
гл
-0.16
inst
-0.15
icity
-0.15
ông
-0.15
inf
-0.14
/msg
-0.14
weed
-0.14
umi
-0.14
oodle
-0.14
Mand
-0.14
POSITIVE LOGITS
eyen
0.15
uzzer
0.14
irl
0.14
ChÃŃ
0.14
chÃŃ
0.14
oley
0.14
âĹĦ
0.14
æĿ¥æºIJ
0.13
hairs
0.13
/unit
0.13
Activations Density 0.012%