INDEX
Explanations
interrogative phrases and expressions of confusion or skepticism
New Auto-Interp
Negative Logits
мәкал
-0.79
AddTagHelper
-0.78
تقاوى
-0.65
"..\..\..\
-0.63
principalColumn
-0.62
sumpay
-0.61
UseVisualStyle
-0.60
""],
-0.59
ۜ
-0.59
"..\..\
-0.58
POSITIVE LOGITS
rungsseite
0.72
?
0.70
?
0.68
?"
0.65
?(
0.65
'?
0.64
؟
0.64
?”
0.64
"?
0.62
?")
0.62
Activations Density 0.297%