INDEX
Explanations
information about political positions and careers
New Auto-Interp
Negative Logits
presidential
-0.17
Ãĸn
-0.16
å½¹
-0.15
ihn
-0.15
Fle
-0.14
Presidential
-0.14
reau
-0.14
cono
-0.14
ernes
-0.14
dilig
-0.14
POSITIVE LOGITS
atron
0.19
ynchronously
0.17
pedia
0.17
abei
0.16
bak
0.15
Duck
0.15
.scalablytyped
0.14
ÙĨص
0.14
perf
0.14
ansi
0.14
Activations Density 0.064%