INDEX
    Explanations

    the beginning of a document or section header

    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.83
    RectangleBorder
    -0.77
     myſelf
    -0.74
    StructEnd
    -0.73
     Monfieur
    -0.71
     مشين
    -0.71
     Efq
    -0.69
    FormTagHelper
    -0.67
    Personensuche
    -0.67
    󠁴
    -0.66
    POSITIVE LOGITS
     matching
    0.75
     Matching
    0.68
     match
    0.68
    Equal
    0.66
     equal
    0.65
     matched
    0.65
    matching
    0.64
     compare
    0.64
    Matching
    0.63
    compare
    0.63
    Act Density 0.091%

    No Known Activations