INDEX
Explanations
terms related to combat activities such as sparring, dueling, and fencing
terms related to sparring and competitive sports
New Auto-Interp
Negative Logits
ovo
-0.76
pora
-0.68
OV
-0.68
oeuv
-0.67
unia
-0.65
osition
-0.65
ove
-0.63
Advertisement
-0.62
idge
-0.62
leep
-0.62
POSITIVE LOGITS
spar
1.13
duel
1.11
fencing
1.08
swords
0.97
lightsaber
0.96
mathemat
0.92
sab
0.78
Duel
0.74
guiActiveUn
0.73
ãĥ£
0.73
Activations Density 0.019%