INDEX
Explanations
instances of discussion topics or categories related to specific forums or threads
New Auto-Interp
Negative Logits
addCriterion
-0.17
iken
-0.16
hd
-0.16
alus
-0.15
etter
-0.15
elor
-0.14
اÙĪÙĨ
-0.14
dra
-0.14
OMIT
-0.14
emoc
-0.14
POSITIVE LOGITS
Off
0.16
pit
0.16
768
0.16
General
0.15
Off
0.15
alt
0.15
General
0.15
auth
0.15
alt
0.15
variants
0.15
Activations Density 0.011%