INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Penny
    -0.08
     kênh
    -0.07
     neutrality
    -0.07
     засід
    -0.07
     urn
    -0.07
     PyTuple
    -0.07
     Reid
    -0.07
    _ud
    -0.07
     Net
    -0.06
    	It
    -0.06
    POSITIVE LOGITS
     strokes
    0.11
     stroke
    0.10
    -strokes
    0.09
    olo
    0.08
     Flo
    0.08
    :
    0.07
    cho
    0.07
     Stroke
    0.07
    0.07
     Stokes
    0.07
    Act Density 0.005%

    No Known Activations