INDEX
Explanations
mentions of video games
references to video games and related terminology
New Auto-Interp
Negative Logits
lain
-0.78
Ket
-0.74
dn
-0.72
nown
-0.72
icons
-0.72
idon
-0.71
esville
-0.70
cycles
-0.70
zynski
-0.70
cule
-0.69
POSITIVE LOGITS
videog
1.06
ame
0.82
opal
0.76
oting
0.74
Theft
0.70
razil
0.70
allo
0.70
ames
0.69
ocument
0.69
OTAL
0.68
Activations Density 0.026%