INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    vt
    -0.07
     Immigration
    -0.07
    croft
    -0.07
    gift
    -0.07
    Stat
    -0.06
    ertil
    -0.06
    plaintext
    -0.06
    Resultado
    -0.06
    —at
    -0.06
     торгов
    -0.06
    POSITIVE LOGITS
     νέ
    0.07
    0.07
    ARGS
    0.06
    蜘蛛
    0.06
    НИ
    0.06
     pravděpodob
    0.06
     seçenek
    0.06
     Micha
    0.06
    .Paint
    0.06
     مثل
    0.06
    Act Density 0.001%

    No Known Activations