INDEX
Explanations
references to popular video game titles and franchises
New Auto-Interp
Negative Logits
/meta
-0.15
enge
-0.15
977
-0.15
Nab
-0.14
mol
-0.14
zung
-0.14
Duel
-0.14
SOR
-0.14
apult
-0.14
ucha
-0.13
POSITIVE LOGITS
Mass
0.39
Bio
0.37
Bi
0.35
Bio
0.34
Mass
0.33
Shepard
0.33
bi
0.31
Bi
0.30
mass
0.29
bi
0.28
Activations Density 0.019%