INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     escaped
    -0.79
     escaping
    -0.70
     escape
    -0.64
     Escape
    -0.63
     escapes
    -0.62
    Escape
    -0.59
    escape
    -0.54
     ESCAPE
    -0.52
    -0.52
    chapp
    -0.44
    POSITIVE LOGITS
    FTFY
    0.94
    tagHelperRunner
    0.83
    ByVersion
    0.79
    ThroughAttribute
    0.79
    0.78
    ConstraintMaker
    0.77
     Wikispecies
    0.76
     فريبيس
    0.76
     Мексичка
    0.76
    ніципа
    0.75
    Act Density 0.009%

    No Known Activations