INDEX
Explanations
references to specific equipment or machinery
New Auto-Interp
Negative Logits
propOrder
-0.54
nahilalakip
-0.52
DockStyle
-0.48
تضيفلها
-0.48
aarrggbb
-0.46
elemField
-0.45
Datuak
-0.44
featureID
-0.44
gráfica
-0.44
StoryboardSegue
-0.43
POSITIVE LOGITS
horses
0.70
horse
0.69
jockey
0.69
trainer
0.67
horsemen
0.66
Breeders
0.64
equine
0.61
silks
0.60
jo
0.59
Saratoga
0.59
Activations Density 0.092%