INDEX
Explanations
details related to family relationships and marital connections
New Auto-Interp
Negative Logits
women
-0.64
Women
-0.59
woman
-0.58
femen
-0.55
WOMEN
-0.55
Women
-0.54
girl
-0.53
women
-0.53
Woman
-0.52
Jason
-0.51
POSITIVE LOGITS
ModelExpression
0.75
Бахар
0.60
Wicidata
0.57
IBOutlet
0.56
rrggbb
0.56
Virginia
0.54
Ann
0.54
ControllerBase
0.53
AndEndTag
0.51
rijden
0.51
Activations Density 0.162%