INDEX
Explanations
expressions of political opinions and concerns
New Auto-Interp
Negative Logits
betweenstory
-0.40
__':
-0.40
acento
-0.37
wijl
-0.37
integrating
-0.37
defining
-0.37
дке
-0.37
tagHelperRunner
-0.37
śli
-0.36
anglès
-0.36
POSITIVE LOGITS
IUrlHelper
0.48
Administrativna
0.47
EndContext
0.45
ValueStyle
0.44
astanza
0.44
billions
0.43
cults
0.41
InjectMocks
0.41
+#+#
0.41
snee
0.40
Activations Density 0.103%