INDEX
Explanations
mentions of the name "Kat" or related variations
New Auto-Interp
Negative Logits
orio
-0.17
ico
-0.16
oran
-0.16
enko
-0.15
edio
-0.15
auf
-0.14
682
-0.14
779
-0.14
icked
-0.14
urg
-0.14
POSITIVE LOGITS
apult
0.25
inka
0.22
rina
0.21
rine
0.21
teg
0.21
anning
0.20
mand
0.19
utura
0.19
zung
0.19
olicy
0.19
Activations Density 0.008%