INDEX
Explanations
attends to list item tokens from the closing list item token
New Auto-Interp
Head Attr Weights
0:0.10
1:0.18
2:0.09
3:0.06
4:0.14
5:0.25
6:0.06
7:0.07
Negative Logits
autorytatywna
-0.35
stället
-0.31
์ตูน
-0.26
racine
-0.25
assertNull
-0.25
سكانية
-0.24
disambiguazione
-0.24
execSQL
-0.24
aanbod
-0.24
кроме
-0.24
POSITIVE LOGITS
ViewFeatures
0.38
PostExecute
0.35
IBOutlet
0.35
Mies
0.33
luiting
0.32
Iden
0.31
нні
0.31
]];
0.31
Mame
0.30
crucified
0.30
Activations Density 0.004%