INDEX
Explanations
references to libertarianism and related political concepts
fleeing war and libertarian ideology
New Auto-Interp
Negative Logits
addComponent
-0.51
Ender
-0.46
ifen
-0.43
cles
-0.42
Neces
-0.42
alos
-0.41
Bons
-0.40
mons
-0.39
etter
-0.39
الفت
-0.39
POSITIVE LOGITS
omsday
0.65
famed
0.65
ImageContext
0.60
fleeing
0.58
Beirut
0.58
plist
0.57
racist
0.56
utopian
0.54
kasarigan
0.54
paille
0.53
Activations Density 0.007%