INDEX
Explanations
German noble titles
occurrences of the name "von" and related names in various contexts
New Auto-Interp
Negative Logits
gallery
-0.86
taboola
-0.81
uyomi
-0.76
inals
-0.71
lighting
-0.71
holders
-0.70
ij士
-0.67
inates
-0.65
uilt
-0.65
rentice
-0.65
POSITIVE LOGITS
Braun
0.82
Frey
0.81
Von
0.74
wald
0.73
neg
0.72
env
0.72
Rothschild
0.72
vol
0.72
von
0.71
der
0.71
Activations Density 0.018%