INDEX
Explanations
affiliate links
mentions of affiliate links or affiliations
New Auto-Interp
Negative Logits
ppo
-0.78
sen
-0.76
STD
-0.75
assetsadobe
-0.74
sa
-0.72
pp
-0.71
ests
-0.71
src
-0.70
iard
-0.69
ppy
-0.69
POSITIVE LOGITS
iliate
1.01
affiliate
0.97
iliated
0.83
henko
0.81
ende
0.70
billing
0.68
merce
0.68
recru
0.67
holder
0.67
affiliates
0.66
Activations Density 0.015%