INDEX
    Explanations

    Quotations and code

    New Auto-Interp
    Negative Logits
    .za
    -0.07
    (AT
    -0.07
    Layout
    -0.06
     insult
    -0.06
     imkân
    -0.06
     threatened
    -0.06
    иля
    -0.06
    _team
    -0.06
    Offset
    -0.06
    -level
    -0.06
    POSITIVE LOGITS
     모두
    0.06
    ứa
    0.06
     لو
    0.06
     skup
    0.06
     براى
    0.06
     رشته
    0.06
     AAP
    0.06
    %M
    0.06
     Kil
    0.06
    ADDR
    0.06
    Act Density 0.002%

    No Known Activations