INDEX
Explanations
mentions of financial transactions or monetary figures
New Auto-Interp
Negative Logits
ljen
-0.43
UserScript
-0.42
pozycji
-0.40
IntentFilter
-0.39
pierw
-0.38
kasarigan
-0.38
czegó
-0.37
crizione
-0.37
ParseException
-0.36
AttributeSet
-0.36
POSITIVE LOGITS
other
3.77
other
3.27
Other
2.95
Other
2.91
autres
2.89
autres
2.88
otros
2.82
otras
2.76
OTHER
2.71
others
2.66
Activations Density 1.624%