INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.98
    )"),
    -0.93
    ArrowToggle
    -0.93
    InjectAttribute
    -0.91
     Majefty
    -0.90
     myſelf
    -0.90
     pleaſure
    -0.89
     defaultstate
    -0.89
    extAlignment
    -0.89
    WireFormat
    -0.86
    POSITIVE LOGITS
     I
    0.51
     o
    0.49
     and
    0.48
     IS
    0.48
     on
    0.48
     when
    0.46
     of
    0.44
     ha
    0.44
     Ha
    0.43
     to
    0.43
    Act Density 0.638%

    No Known Activations