INDEX
Explanations
references to a character named Joan, particularly in historical or narrative contexts
New Auto-Interp
Negative Logits
vie
-0.18
ensch
-0.15
iens
-0.15
Insecta
-0.15
yan
-0.14
yu
-0.14
booming
-0.14
yen
-0.14
yal
-0.14
lich
-0.14
POSITIVE LOGITS
athan
0.20
strict
0.17
oven
0.15
neau
0.15
athon
0.15
idel
0.14
lant
0.14
Ù쨳
0.14
ildo
0.14
_mirror
0.14
Activations Density 0.011%