INDEX
Explanations
words related to martial arts
references to martial arts and related terminology
New Auto-Interp
Negative Logits
RGB
-0.79
idy
-0.78
ilk
-0.75
apter
-0.75
ources
-0.69
Merrill
-0.68
orb
-0.68
uter
-0.67
ummer
-0.67
bos
-0.66
POSITIVE LOGITS
martial
1.00
arts
1.00
fighting
0.90
prowess
0.83
practitioners
0.81
doms
0.78
chops
0.77
spar
0.75
inho
0.74
abilia
0.74
Activations Density 0.020%