INDEX
Explanations
numerical values and statistics regarding scoring or performance
New Auto-Interp
Negative Logits
маз
-0.15
bnb
-0.14
-Ray
-0.14
ounding
-0.14
Sab
-0.14
atie
-0.14
abyte
-0.13
Johns
-0.13
.radioButton
-0.13
_FWD
-0.13
POSITIVE LOGITS
-го
0.15
ritch
0.15
ropdown
0.15
erness
0.15
emale
0.15
ìĤ´
0.14
ساÙĦÙĩ
0.14
Craig
0.14
Všech
0.14
otch
0.14
Activations Density 0.200%