INDEX
Explanations
references to combat or fighter mechanics in games
New Auto-Interp
Negative Logits
384
-0.16
Insn
-0.15
achi
-0.15
upal
-0.15
371
-0.15
odyn
-0.14
oky
-0.14
inen
-0.14
ipsis
-0.14
.mods
-0.14
POSITIVE LOGITS
Gap
0.16
ken
0.16
ammer
0.15
arel
0.14
kin
0.14
gap
0.14
ابر
0.14
flooded
0.14
dead
0.14
ICLE
0.14
Activations Density 0.023%