INDEX
Explanations
greetings or informal forms of address like 'Hey'
instances of greetings or salutations
New Auto-Interp
Negative Logits
rall
-0.69
Awakens
-0.66
minist
-0.65
destro
-0.65
aic
-0.64
violation
-0.64
ossibility
-0.63
rehens
-0.63
ators
-0.63
idation
-0.63
POSITIVE LOGITS
hey
1.04
hey
1.02
guys
0.99
prest
0.96
bye
0.89
Hey
0.88
Guys
0.83
Hey
0.83
boys
0.80
oka
0.78
Activations Density 0.014%