INDEX
Explanations
statistical data regarding beliefs and demographics
New Auto-Interp
Negative Logits
ret
-0.16
hek
-0.15
trust
-0.15
ussy
-0.14
clot
-0.14
Black
-0.14
olean
-0.14
issy
-0.14
uma
-0.14
ctl
-0.14
POSITIVE LOGITS
dime
0.17
kol
0.15
ÄĻd
0.15
ÑĢаÑģ
0.15
itest
0.15
utenberg
0.14
yme
0.14
ropic
0.14
-www
0.14
readcr
0.14
Activations Density 0.002%