INDEX
Explanations
contact information like email addresses and social media handles
mentions of social media platforms and contact information
New Auto-Interp
Negative Logits
isers
-0.71
hallucinations
-0.68
aez
-0.68
¶
-0.65
emen
-0.65
othal
-0.64
buildup
-0.64
buffs
-0.64
needed
-0.63
edIn
-0.63
POSITIVE LOGITS
tradem
0.90
www
0.80
Ticket
0.77
Leban
0.75
pione
0.74
lez
0.72
Website
0.72
0.71
tainment
0.71
subscribe
0.71
Activations Density 0.142%