INDEX
Explanations
references to Chinese cultural elements and themes
New Auto-Interp
Negative Logits
_KP
-0.18
ãģ¿
-0.17
edik
-0.16
Neg
-0.15
quin
-0.15
ë²Į
-0.15
بÙĪØ§Ø³Ø·Ø©
-0.14
isphere
-0.14
atatype
-0.14
FN
-0.14
POSITIVE LOGITS
Jackie
0.26
Ip
0.21
Jet
0.21
Sha
0.20
Chow
0.20
Jet
0.20
uten
0.19
Shaw
0.18
Sha
0.18
sha
0.18
Activations Density 0.023%