INDEX
Explanations
names or titles with 'von' in them
mentions of the name "Von."
New Auto-Interp
Negative Logits
gallery
-0.82
uyomi
-0.82
taboola
-0.82
lighting
-0.73
dress
-0.72
inals
-0.68
Ĥª
-0.68
colour
-0.67
MpServer
-0.66
rew
-0.66
POSITIVE LOGITS
Braun
0.86
Von
0.84
von
0.76
Frey
0.75
der
0.74
Karma
0.74
forcer
0.74
hof
0.73
Schwarz
0.72
env
0.72
Activations Density 0.011%