INDEX
Explanations
references to the word "Pink" with varying intensities
references to the word "Pink."
New Auto-Interp
Negative Logits
Interstitial
-0.84
BIL
-0.74
UST
-0.74
SCHOOL
-0.70
DISTR
-0.69
BILITY
-0.68
ä¿
-0.68
taboola
-0.68
à¨
-0.68
CLASS
-0.67
POSITIVE LOGITS
erton
1.11
Pink
1.02
Floyd
1.02
ertodd
0.89
Pink
0.86
erson
0.83
Unicorn
0.82
Panther
0.80
enberg
0.80
Sparkle
0.79
Activations Density 0.008%