INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.94
    osta
    -0.89
    ostic
    -0.78
    OLOG
    -0.78
     GOODMAN
    -0.73
    atche
    -0.72
    ivist
    -0.72
    kefeller
    -0.71
    abwe
    -0.71
    ibaba
    -0.71
    POSITIVE LOGITS
    nesday
    1.00
     couples
    0.95
     equality
    0.88
     marry
    0.86
    equality
    0.82
     divorce
    0.80
     married
    0.79
    wife
    0.79
     monog
    0.79
     marrying
    0.77
    Act Density 0.696%

    No Known Activations