INDEX
Explanations
proper names of individuals
mentions of prominent individuals associated with political discourse
New Auto-Interp
Negative Logits
Confederation
-0.72
knit
-0.69
MEN
-0.68
ModLoader
-0.65
20439
-0.64
knit
-0.62
>>\
-0.61
ashtra
-0.60
Women
-0.58
nav
-0.57
POSITIVE LOGITS
.,
0.85
Abrams
0.82
linger
0.81
iggins
0.76
inton
0.76
isson
0.74
agan
0.73
isner
0.71
ample
0.71
Mull
0.70
Activations Density 0.111%