INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -cell
    -0.07
    <Comment
    -0.07
     Battlefield
    -0.06
     comprom
    -0.06
    teborg
    -0.06
    -0.06
    (sym
    -0.06
     Lexer
    -0.06
    _layout
    -0.06
     commentator
    -0.06
    POSITIVE LOGITS
     Ig
    0.11
    @register
    0.07
     RG
    0.07
     Ir
    0.07
     I
    0.07
    "x
    0.07
     Hodg
    0.07
    ög
    0.07
     IG
    0.06
    g
    0.06
    Act Density 0.003%

    No Known Activations