INDEX
Explanations
mentions of the term "men" and its variations in various contexts
New Auto-Interp
Negative Logits
ighton
-0.17
leigh
-0.16
ahn
-0.15
edin
-0.15
oslav
-0.14
UMB
-0.14
èĭ
-0.14
eren
-0.14
imler
-0.14
erc
-0.14
POSITIVE LOGITS
opause
0.26
endez
0.23
cken
0.23
ial
0.21
acing
0.21
ubar
0.20
ager
0.20
iscal
0.20
folk
0.19
op
0.19
Activations Density 0.025%