INDEX
Explanations
expressions of love and affection
New Auto-Interp
Negative Logits
vida
-0.15
zeich
-0.15
anton
-0.15
uminium
-0.14
upply
-0.14
vid
-0.14
agem
-0.14
ĵ¨
-0.14
aze
-0.13
izio
-0.13
POSITIVE LOGITS
ossier
0.15
OLON
0.14
oure
0.14
Král
0.14
kill
0.14
-at
0.14
shint
0.13
kıl
0.13
ÙĬراÙĨ
0.13
isman
0.13
Activations Density 0.025%