INDEX
Explanations
components related to political and campaign activities
New Auto-Interp
Negative Logits
er
-0.22
ity
-0.15
ÙĬ
-0.15
ãĥ£
-0.15
vrier
-0.15
аÑĢ
-0.14
vise
-0.14
Xem
-0.14
ãĥ¥
-0.14
entre
-0.13
POSITIVE LOGITS
and
0.18
lined
0.14
rops
0.14
or
0.14
atron
0.14
acre
0.13
lobal
0.13
سÙħØ©
0.13
Ìģ
0.13
-www
0.13
Activations Density 0.341%