INDEX
Explanations
class and variable definitions
New Auto-Interp
Negative Logits
roupa
0.45
kênh
0.44
bebê
0.42
arele
0.42
высокие
0.41
naturais
0.41
वाट
0.41
الطبي
0.40
serviceTime
0.40
_____________
0.40
POSITIVE LOGITS
class
0.68
summary
0.66
Summary
0.63
summary
0.59
overview
0.56
Overview
0.54
subclasses
0.53
Summary
0.52
SUMMARY
0.52
annotated
0.51
Activations Density 0.003%