INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.85
     EconPapers
    -0.82
    omock
    -0.76
    }';
    -0.76
    AnchorStyles
    -0.72
    AntiForgeryToken
    -0.70
    ActivityCompat
    -0.69
    apnews
    -0.69
    ArrowToggle
    -0.69
     ivelany
    -0.69
    POSITIVE LOGITS
     WHEN
    0.84
     when
    0.83
    When
    0.82
     When
    0.80
    when
    0.77
    WHEN
    0.69
    cuando
    0.67
    Quando
    0.67
    Cuando
    0.67
     cuándo
    0.64
    Act Density 0.116%

    No Known Activations