INDEX
Explanations
punctuation and sentence structure
New Auto-Interp
Negative Logits
ENCHMARK
-0.15
riad
-0.14
İY
-0.14
omon
-0.14
926
-0.14
inux
-0.14
θε
-0.14
lob
-0.14
apl
-0.14
ãĤ¤ãĥ¤
-0.14
POSITIVE LOGITS
Garc
0.31
gar
0.25
Rencontre
0.21
Elev
0.19
camb
0.19
extract
0.19
Camb
0.18
PURE
0.18
appetite
0.18
scams
0.17
Activations Density 0.001%