INDEX
Explanations
references to the character Caitlin
New Auto-Interp
Negative Logits
egas
-0.17
agnost
-0.16
neau
-0.15
yk
-0.15
kker
-0.15
atta
-0.15
aget
-0.14
ettel
-0.14
ision
-0.14
ë¥ĺ
-0.14
POSITIVE LOGITS
lyn
0.31
lin
0.28
ano
0.16
inati
0.15
lan
0.15
LIN
0.15
olic
0.15
lÃŃn
0.15
abr
0.15
-ln
0.15
Activations Density 0.007%