INDEX
Explanations
numerical data or figures related to sports or statistics
New Auto-Interp
Negative Logits
TagMode
-0.69
transfieras
-0.68
KommentareTeilen
-0.67
externi
-0.58
featureID
-0.56
EndContext
-0.49
استنادى
-0.48
ReusableCell
-0.46
kloped
-0.45
//
-0.44
POSITIVE LOGITS
alanta
0.63
sterilization
0.60
operatorname
0.59
S
0.59
'\\;'
0.58
magari
0.58
thermoc
0.57
Și
0.57
frattempo
0.57
automatica
0.57
Activations Density 0.426%