INDEX
Explanations
words related to fast movement or growth
references to fast food
New Auto-Interp
Negative Logits
Seym
-0.89
pheus
-0.86
xual
-0.81
eryl
-0.78
vironment
-0.77
cules
-0.74
illary
-0.72
ignty
-0.71
代
-0.70
Theater
-0.69
POSITIVE LOGITS
idious
1.45
paced
1.33
eners
1.10
ened
1.06
cgi
0.94
ener
0.93
ening
0.88
nesses
0.88
running
0.86
asleep
0.84
Activations Density 0.025%