INDEX
    Explanations

    references to music artists and their associations with badges or rewards

    New Auto-Interp
    Negative Logits
    ding
    -0.87
    igating
    -0.84
    pse
    -0.80
    ded
    -0.80
    mented
    -0.78
    ersed
    -0.77
    igation
    -0.76
    igators
    -0.76
    tank
    -0.75
    ezvous
    -0.75
    POSITIVE LOGITS
    kers
    0.82
    ker
    0.74
     Brach
    0.70
    Zip
    0.69
    cko
    0.68
     Haram
    0.66
    umper
    0.64
     Neh
    0.63
     Boys
    0.61
    Constructed
    0.60
    Act Density 0.173%

    No Known Activations