INDEX
Explanations
instances of people making statements or comments
New Auto-Interp
Negative Logits
980
-0.19
585
-0.14
795
-0.14
opus
-0.13
andy
-0.13
EXT
-0.13
ext
-0.13
_fsm
-0.13
ucid
-0.13
736
-0.13
POSITIVE LOGITS
ewidth
0.16
alama
0.15
.documentation
0.15
ethyst
0.14
Rey
0.14
perms
0.14
ails
0.14
éģĵ
0.14
decltype
0.14
gar
0.14
Activations Density 0.016%