INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    posterous
    0.71
    Укупно
    0.69
    ReadToEnd
    0.68
    व्
    0.67
    👻
    0.66
     पसर
    0.65
    stava
    0.63
    ardan
    0.63
    0.63
     shrug
    0.62
    POSITIVE LOGITS
     specific
    4.65
    specific
    4.23
    Specific
    4.20
     Specific
    4.11
     específica
    3.79
     específico
    3.79
     específicos
    3.70
     specifico
    3.66
     spécifique
    3.63
     específicas
    3.62
    Act Density 2.054%

    No Known Activations