INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    	static
    -0.07
     Director
    -0.07
    .print
    -0.06
    Maker
    -0.06
    .Equals
    -0.06
     typography
    -0.06
    .Invariant
    -0.06
    (writer
    -0.06
     replaces
    -0.06
    static
    -0.06
    POSITIVE LOGITS
     Plugins
    0.07
     {{{
    0.07
    0.07
     üst
    0.06
    ButtonItem
    0.06
    ครอบ
    0.06
     دین
    0.06
    >↵↵
    0.06
    /embed
    0.06
     chín
    0.06
    Act Density 0.009%

    No Known Activations