INDEX
    Explanations

    the name "Mario"

    mentions of the name "Mario" and variations of it, along with some references to "Luigi."

    New Auto-Interp
    Negative Logits
    ORE
    -0.75
    ribune
    -0.73
    ivities
    -0.72
    angers
    -0.70
    aylor
    -0.67
    oning
    -0.65
    ij士
    -0.64
     warrants
    -0.64
    orians
    -0.63
    lace
    -0.63
    POSITIVE LOGITS
     Kart
    1.27
     Luigi
    1.17
     Mario
    1.14
    Mario
    1.03
     Bros
    0.87
     Cuomo
    0.85
     Pik
    0.82
    Maker
    0.79
     Wii
    0.79
     Maker
    0.79
    Act Density 0.007%

    No Known Activations