INDEX
Explanations
mentions of the name "Catherine" and its variations
New Auto-Interp
Negative Logits
idot
-0.16
aru
-0.15
OnError
-0.15
othy
-0.14
anal
-0.14
atty
-0.14
oner
-0.14
chwitz
-0.14
mapper
-0.14
InOut
-0.14
POSITIVE LOGITS
ittal
0.18
wheels
0.15
eresa
0.15
ETS
0.14
Wheels
0.14
Serious
0.14
enan
0.14
oggle
0.14
Tate
0.14
bam
0.14
Activations Density 0.013%