INDEX
Explanations
references to names, particularly those of notable women
New Auto-Interp
Negative Logits
etine
-0.17
.GroupLayout
-0.16
blr
-0.16
Nisan
-0.16
iff
-0.15
šet
-0.15
WithIdentifier
-0.14
anson
-0.14
vap
-0.14
ldkf
-0.14
POSITIVE LOGITS
Plain
0.17
mary
0.16
Elizabeth
0.16
thread
0.15
-Mar
0.15
plain
0.15
amar
0.14
beth
0.14
Ann
0.14
.pivot
0.14
Activations Density 0.275%