INDEX
Explanations
the start of new sections or ideas in a document
New Auto-Interp
Negative Logits
://$
-0.68
HomeController
-0.60
zsef
-0.58
hirts
-0.57
цездатний
-0.56
__((
-0.55
pokok
-0.54
atru
-0.54
Życiorys
-0.54
-0.53
POSITIVE LOGITS
expand
1.60
Expand
1.35
expanded
1.27
expands
1.25
expanding
1.18
Expanding
1.18
expand
1.14
expansion
1.13
Expanding
1.09
Expand
1.08
Activations Density 0.027%