INDEX
Explanations
incidents involving law enforcement and driving under the influence
New Auto-Interp
Negative Logits
الحره
-0.52
ModelExpression
-0.51
ंदीखरीदारी
-0.48
defaultstate
-0.47
AddHtmlAttribute
-0.47
сылкі
-0.43
BeginInit
-0.42
tartalomajánló
-0.40
addContainerGap
-0.40
Ссылки
-0.40
POSITIVE LOGITS
DUI
0.65
driving
0.63
driver
0.63
chauffeur
0.59
Driving
0.59
Driver
0.57
drunk
0.56
Driving
0.52
Driver
0.51
motorista
0.48
Activations Density 0.154%