INDEX
Explanations
expressions of excitement or emphasis in conversations
New Auto-Interp
Negative Logits
COPYING
-0.17
preg
-0.15
azzi
-0.15
readers
-0.14
idot
-0.14
Filed
-0.14
Funny
-0.14
غاز
-0.14
Categories
-0.13
alama
-0.13
POSITIVE LOGITS
edited
0.30
edit
0.29
edit
0.28
EDIT
0.28
Edit
0.27
/Edit
0.26
Edit
0.26
Edited
0.26
EDIT
0.24
ETA
0.23
Activations Density 0.192%