INDEX
    Explanations

    punctuation marks and white spaces

    Punctuation or special characters

    New Auto-Interp
    Negative Logits
    ,
    -1.08
    .
    -0.81
    :
    -0.80
    ...
    -0.72
    ;
    -0.70
    )
    -0.69
    /
    -0.68
     em
    -0.67
     di
    -0.67
    -
    -0.66
    POSITIVE LOGITS
    };*/
    1.02
     Италијани
    0.94
    ")));
    
    0.90
     }}$.
    0.89
    }.
    
    0.88
    ThroughAttribute
    0.88
    '])->
    0.87
    ).}
    0.87
    theless
    0.85
    ']))
    
    0.85
    Act Density 0.031%

    No Known Activations