INDEX
    Explanations

    names, titles, and designations related to music and awards

    New Auto-Interp
    Negative Logits
    ged
    -0.83
    ted
    -0.79
    rossed
    -0.75
    ounted
    -0.72
    GED
    -0.71
    iked
    -0.70
    reciated
    -0.69
    ourced
    -0.68
    TED
    -0.67
    aked
    -0.66
    POSITIVE LOGITS
     Roskov
    0.82
    fony
    0.82
    Dmit
    0.79
     esternos
    0.79
     Chwiliwch
    0.79
    Portail
    0.79
    newBuilder
    0.77
    Pautan
    0.77
    enumi
    0.76
     Dmit
    0.76
    Act Density 4.870%

    No Known Activations