INDEX
Explanations
words related to the concept of 'ninja'
references to ninja and samurai themes in pop culture
New Auto-Interp
Negative Logits
orthern
-0.88
bach
-0.87
rose
-0.80
iers
-0.79
itional
-0.79
orf
-0.79
notes
-0.78
ighton
-0.77
fman
-0.77
opol
-0.77
POSITIVE LOGITS
Turtles
0.97
Turtle
0.71
Haram
0.68
haircut
0.68
llan
0.67
Buddha
0.67
Rico
0.65
zzi
0.63
ilt
0.63
skate
0.62
Activations Density 0.028%