INDEX
Explanations
concepts related to political revolutions
references to revolutionary movements or concepts
New Auto-Interp
Negative Logits
butt
-0.68
paragraph
-0.66
epad
-0.66
skip
-0.65
contact
-0.65
WAYS
-0.59
visual
-0.59
Choice
-0.58
Skip
-0.58
thy
-0.57
POSITIVE LOGITS
aries
1.10
naire
1.02
aire
0.92
eering
0.92
arily
0.89
aires
0.87
ocrat
0.86
uphe
0.86
eers
0.83
revolutions
0.83
Activations Density 0.025%