INDEX
Explanations
references to the video game "World of Warcraft" and the term "vanilla."
terms related to popular video games and specific phrases indicating gameplay features
New Auto-Interp
Negative Logits
anish
-0.86
hod
-0.74
lasses
-0.70
Laksh
-0.70
interstitial
-0.69
omi
-0.69
ract
-0.68
Lamp
-0.67
chens
-0.66
LOS
-0.65
POSITIVE LOGITS
Furious
1.91
Warcraft
1.83
vanilla
1.79
Vanilla
1.58
Wo
1.49
Mog
1.36
Wo
1.34
talk
1.32
Van
1.23
Woo
0.99
Activations Density 0.037%