INDEX
    Explanations

    emotional expressions or sentiments related to relationships and personal experiences

    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.76
     صوتيه
    -0.72
    astéroïdes
    -0.59
     canadien
    -0.59
    <bos>
    -0.58
    ContentAlignment
    -0.58
     okuyayım
    -0.57
    AutoScaleMode
    -0.57
    pagnol
    -0.57
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
    ")));
    
    0.56
    "},
    
    0.55
    "]));
    0.54
    %
    
    0.53
     CanadaChoose
    0.53
    "));
    
    0.51
     bim
    0.51
    Datuak
    0.50
     {};
    
    0.50
     }}$}
    0.50
    Act Density 0.049%

    No Known Activations