INDEX
Explanations
references to specific individuals, particularly those with the name "Vel."
New Auto-Interp
Negative Logits
iba
-0.16
.createFrom
-0.15
eme
-0.15
SCORE
-0.15
iff
-0.15
SCORE
-0.15
neau
-0.14
alus
-0.14
ellar
-0.14
flip
-0.14
POSITIVE LOGITS
ocities
0.23
Vel
0.22
vel
0.20
kommen
0.18
Vel
0.17
oce
0.17
adero
0.17
áz
0.16
еÑĢеÑĩ
0.16
indre
0.16
Activations Density 0.014%