INDEX
Explanations
names that begin with Marg and related variations of that name
New Auto-Interp
Negative Logits
essler
-0.08
yon
-0.07
etary
-0.07
jaw
-0.07
oog
-0.06
stra
-0.06
dra
-0.06
天
-0.06
eing
-0.06
ÅĤ
-0.06
POSITIVE LOGITS
uer
0.09
inal
0.09
inalg
0.08
inals
0.08
ally
0.08
rove
0.08
aret
0.07
eline
0.07
borough
0.07
anne
0.07
Activations Density 0.004%