INDEX
Explanations
proper nouns or words related to combat
names of characters and terms related to combat and significant actions in narratives
New Auto-Interp
Negative Logits
iflower
-0.80
sburgh
-0.78
oured
-0.78
owship
-0.77
sworth
-0.76
DonaldTrump
-0.74
ivity
-0.74
worthy
-0.72
ivities
-0.70
worthiness
-0.69
POSITIVE LOGITS
rolet
0.92
Mou
0.89
cedes
0.73
Esports
0.72
WWF
0.69
zik
0.66
zer
0.66
xp
0.65
Introduced
0.65
veyard
0.65
Activations Density 0.020%