INDEX
Explanations
attends to the "which" and "whether" token patterns from their corresponding later tokens marked with "of" or "not"
New Auto-Interp
Head Attr Weights
0:0.13
1:0.37
2:0.11
3:0.04
4:0.04
5:0.03
6:0.04
7:0.19
Negative Logits
IBOutlet
-0.49
EndInit
-0.40
PostExecute
-0.39
ResumeLayout
-0.38
'{@-0.36
InjectAttribute
-0.36
OGND
-0.35
AttributeSet
-0.35
yscy
-0.35
addCriterion
-0.35
POSITIVE LOGITS
✨:
0.40
Kette
0.40
referenties
0.39
EconPapers
0.36
Wappen
0.34
νό
0.33
blessé
0.33
padek
0.33
circulaire
0.33
sauvages
0.33
Activations Density 0.334%