INDEX
Explanations
references to political candidates and their backgrounds, particularly in the context of elections
New Auto-Interp
Negative Logits
agini
-0.17
erca
-0.16
DIAG
-0.15
imetype
-0.15
Bun
-0.14
solo
-0.14
erno
-0.14
ήÏĤ
-0.14
o
-0.14
ose
-0.14
POSITIVE LOGITS
ORIA
0.14
ãĥ¼ãĥį
0.14
isky
0.14
'#
0.14
ë¸Į
0.14
ulary
0.13
ãĤ«ãĥ¼
0.13
_CPP
0.13
_SOC
0.13
_thumbnail
0.13
Activations Density 0.109%