INDEX
Explanations
references to the name "Mario"
references to the character "Mario" from video games
New Auto-Interp
Negative Logits
aylor
-0.94
ORE
-0.81
arget
-0.81
ynski
-0.78
Ö¼
-0.75
umbnails
-0.73
oring
-0.72
icles
-0.72
Newsp
-0.71
ij士
-0.70
POSITIVE LOGITS
Kart
1.25
Cuomo
0.98
Luigi
0.93
Bros
0.91
Mario
0.86
Maker
0.86
Polo
0.80
Maker
0.79
Gomez
0.74
Drag
0.72
Activations Density 0.019%