INDEX
    Explanations

    mentions of celebrities and notable public figures

    New Auto-Interp
    Negative Logits
     giornal
    -0.40
    ://
    -0.38
    ://"
    -0.38
     пожалуйста
    -0.38
    seq
    -0.38
     större
    -0.37
    RectangleBorder
    -0.37
     naturligt
    -0.36
     voltak
    -0.36
     érz
    -0.36
    POSITIVE LOGITS
     Administrativna
    0.84
    .*")]
    0.82
     Italijani
    0.82
    Jährige
    0.80
     */
    
    
    0.77
     referrerpolicy
    0.74
     CommandType
    0.74
    FunctionFlags
    0.73
    centralwidget
    0.73
    Hozzáférés
    0.73
    Act Density 0.197%

    No Known Activations