INDEX
Explanations
numeric representations of age or quantities
New Auto-Interp
Negative Logits
Orrell
-0.91
الحره
-0.76
es
-0.73
IBinder
-0.71
raszam
-0.66
mukaan
-0.66
TextAppearance
-0.65
av
-0.62
?>">
-0.61
men
-0.61
POSITIVE LOGITS
twenty
1.20
forty
1.18
seventy
1.18
twenty
1.17
sixty
1.13
eighty
1.11
thirty
1.10
fifty
1.06
forty
1.05
ninety
1.05
Activations Density 0.053%