INDEX
Explanations
references to video game-related themes and critiques
New Auto-Interp
Negative Logits
inar
-0.15
ROTO
-0.14
umblr
-0.14
uppet
-0.13
gymn
-0.13
quito
-0.13
Toolkit
-0.13
astro
-0.13
opo
-0.13
Bik
-0.13
POSITIVE LOGITS
gaming
0.49
video
0.44
console
0.43
games
0.42
game
0.39
Gaming
0.38
console
0.37
consoles
0.37
Video
0.36
gamer
0.36
Activations Density 0.431%