INDEX
Explanations
mentions of academic titles, specifically "professor."
New Auto-Interp
Negative Logits
asonic
-0.15
ivet
-0.15
forms
-0.15
elog
-0.15
edes
-0.14
ough
-0.14
Bits
-0.14
AZY
-0.14
еп
-0.14
ót
-0.14
POSITIVE LOGITS
ial
0.27
ship
0.19
à¥Ģय
0.18
Emer
0.17
taire
0.17
ession
0.17
iate
0.16
anity
0.16
iginal
0.16
anes
0.16
Activations Density 0.016%