INDEX
Explanations
descriptions of physical appearance and characteristics
New Auto-Interp
Negative Logits
868
-0.16
eye
-0.15
924
-0.15
242
-0.15
tongue
-0.14
bras
-0.14
976
-0.14
riba
-0.14
Jihad
-0.14
XHR
-0.14
POSITIVE LOGITS
iyas
0.18
éĻ¢
0.16
_Frame
0.15
лл
0.14
tattoos
0.14
framing
0.14
_MM
0.14
fairness
0.14
ARGE
0.13
coarse
0.13
Activations Density 0.161%