INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     dex
    -0.10
     esc
    -0.07
     dw
    -0.07
    >>,
    -0.07
     w
    -0.07
     خر
    -0.07
     percept
    -0.07
     AF
    -0.07
    -0.07
    _in
    -0.07
    POSITIVE LOGITS
     dirig
    0.08
    Conven
    0.08
     Boo
    0.08
     conven
    0.08
    Houston
    0.08
     consol
    0.07
    0.07
     Bart
    0.07
     Payne
    0.07
    0.07
    Act Density 0.005%

    No Known Activations