INDEX
    Explanations

    personal pronouns expressing ownership or involvement

    New Auto-Interp
    Negative Logits
     srf
    -0.96
    ritz
    -0.86
    atown
    -0.80
    achus
    -0.80
    uben
    -0.77
    rike
    -0.77
     Collider
    -0.76
    emetery
    -0.75
    pless
    -0.75
    arnaev
    -0.75
    POSITIVE LOGITS
    ³³³³³³³³
    0.72
     Kw
    0.69
    mouth
    0.65
     Grizzlies
    0.65
     Vers
    0.65
     Principle
    0.64
    chief
    0.62
     ãĢĮ
    0.62
     guarant
    0.62
     Dj
    0.61
    Act Density 0.000%

    No Known Activations