INDEX
Explanations
mentions of hair, especially blonde hair and its different styles or attributes
New Auto-Interp
Negative Logits
Flesh
-0.18
erea
-0.17
flesh
-0.14
irt
-0.14
üf
-0.14
eczy
-0.14
ivot
-0.14
еÑĢин
-0.13
Dot
-0.13
htub
-0.13
POSITIVE LOGITS
hair
0.50
Hair
0.42
Hair
0.40
hair
0.38
locks
0.37
blond
0.36
blonde
0.35
髪
0.35
волоÑģ
0.34
curls
0.32
Activations Density 0.107%