INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    criptive
    -0.76
     Sexual
    -0.74
     Alvin
    -0.73
     reembolso
    -0.73
    mett
    -0.72
    ряд
    -0.71
    ADL
    -0.71
     daher
    -0.70
     rapid
    -0.70
    >());
    -0.70
    POSITIVE LOGITS
     contested
    0.98
     leaping
    0.94
     fighting
    0.93
     contesting
    0.89
     securing
    0.84
     jumping
    0.84
     contesto
    0.82
     retrieves
    0.82
     retrieving
    0.81
     collection
    0.81
    Act Density 0.017%

    No Known Activations