INDEX
Explanations
phrases related to political discourse and influence
New Auto-Interp
Negative Logits
ArrowToggle
-0.53
sumpay
-0.52
🇶
-0.51
这件事情
-0.50
zvuky
-0.49
totem
-0.49
Espèce
-0.48
incom
-0.48
eſt
-0.48
lard
-0.48
POSITIVE LOGITS
awtextra
0.70
WireFormatLite
0.66
présent
0.66
bewerken
0.56
Besten
0.56
webElementGuid
0.55
setSource
0.54
UnusedPrivate
0.52
abbond
0.52
HasBeenSet
0.50
Activations Density 0.638%