INDEX
Explanations
commands or actions related to increasing size or visibility
New Auto-Interp
Negative Logits
almo
-0.57
atru
-0.55
bookstore
-0.49
Situs
-0.49
nestjs
-0.48
észet
-0.47
useNavigate
-0.47
Dyck
-0.44
agramm
-0.43
://
-0.43
POSITIVE LOGITS
expand
1.65
Expand
1.47
expands
1.33
expand
1.28
Expanding
1.27
expanded
1.27
expanding
1.20
Expanding
1.18
Expand
1.17
expanding
1.16
Activations Density 0.028%