INDEX
Explanations
references to firearms and their specifications
New Auto-Interp
Negative Logits
arken
-0.17
ernen
-0.16
.Selenium
-0.15
amilia
-0.15
ÑĢаÑħ
-0.15
ends
-0.14
inia
-0.14
Batter
-0.14
bum
-0.14
ahlen
-0.14
POSITIVE LOGITS
Model
0.17
Rug
0.17
folding
0.17
Folding
0.16
Fold
0.15
Folder
0.15
odb
0.15
MODEL
0.15
èŤ
0.15
MESS
0.15
Activations Density 0.080%