INDEX
Explanations
the infinitive form of verbs
New Auto-Interp
Negative Logits
principalTable
-0.57
ainfi
-0.56
виправивши
-0.55
featureID
-0.53
ValueStyle
-0.52
BIÉN
-0.52
ScopeManager
-0.50
miniaturka
-0.50
ligiloj
-0.50
Jereo
-0.50
POSITIVE LOGITS
betweenstory
0.44
Надо
0.43
是为了
0.43
是
0.42
是要
0.42
=('0.41
TO
0.40
Kno
0.40
目的是
0.40
drawing
0.40
Activations Density 0.028%