INDEX
Explanations
biographical information about individuals, including names, birthplaces, and familial relationships
New Auto-Interp
Negative Logits
الرياضيه
-0.52
external
-0.48
bawat
-0.45
stil
-0.44
AuthProvider
-0.43
كورة
-0.42
mentor
-0.42
style
-0.41
resizingMask
-0.41
Weber
-0.41
POSITIVE LOGITS
son
1.52
daughter
1.39
sons
1.37
hijo
1.26
grandson
1.24
Son
1.18
figlio
1.15
Son
1.14
daughters
1.13
Daughter
1.13
Activations Density 0.180%