INDEX
Explanations
political figures and organizations
names and references related to political figures and entities
New Auto-Interp
Negative Logits
displayText
-0.84
ossier
-0.75
uesday
-0.71
endors
-0.68
myster
-0.67
endorsements
-0.66
ilater
-0.65
paycheck
-0.64
ilan
-0.64
POLITICO
-0.63
POSITIVE LOGITS
hend
0.75
droid
0.67
esc
0.65
Nar
0.64
Robot
0.63
Terminal
0.63
hare
0.62
bre
0.62
aroo
0.62
Por
0.61
Activations Density 0.354%