INDEX
Explanations
phrases and concepts related to political candidates and elections
New Auto-Interp
Negative Logits
flat
-0.15
“
-0.15
veh
-0.14
itches
-0.14
Flat
-0.13
-0.13
estinal
-0.13
BO
-0.13
-flat
-0.13
ishes
-0.12
POSITIVE LOGITS
esco
0.14
xz
0.13
Äįel
0.13
اÙĬÙĦ
0.13
idunt
0.13
Alto
0.13
csr
0.13
æŁĦ
0.13
braco
0.13
_nat
0.13
Activations Density 0.148%