INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ”.
    -1.05
    ”,
    -1.01
    ",
    -0.90
    ".
    -0.90
    .
    -0.82
    ’.
    -0.79
    “.
    -0.76
    "]
    -0.75
    '.
    -0.73
    ",
    
    -0.72
    POSITIVE LOGITS
    <bos>
    0.91
    DockStyle
    0.77
     disambiguazione
    0.74
    Vidite
    0.71
    Portale
    0.70
    cifix
    0.66
    клопе
    0.63
    rungsseite
    0.63
     Мексичка
    0.63
     Савезне
    0.61
    Act Density 0.166%

    No Known Activations