INDEX
Explanations
references to the name "Mario"
mentions of the name "Mario."
New Auto-Interp
Negative Logits
aylor
-0.90
arget
-0.74
icles
-0.72
ORE
-0.72
ribune
-0.70
oring
-0.70
ynski
-0.69
lessly
-0.69
ivities
-0.68
ypes
-0.67
POSITIVE LOGITS
Kart
1.31
Luigi
0.98
Cuomo
0.91
Mario
0.91
Polo
0.84
Maker
0.83
Bros
0.80
Maker
0.79
Mario
0.79
Drag
0.77
Activations Density 0.016%