INDEX
Explanations
numerical data and statistics
New Auto-Interp
Negative Logits
ngdoc
-0.68
}\]
-0.50
veien
-0.50
}}-
-0.49
FormTagHelper
-0.49
">',
-0.48
rungsseite
-0.47
Diweddarwch
-0.47
nemlig
-0.47
ידי
-0.46
POSITIVE LOGITS
/
1.84
/
1.44
/
1.28
'/
1.21
$/
1.17
/$
1.13
"/
1.10
'/
1.09
"/
1.07
,/
1.07
Activations Density 0.370%