INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     stroke
    -2.39
    stroke
    -2.28
     Stroke
    -1.89
     strokes
    -1.80
    Stroke
    -1.77
    strokes
    -1.62
    STROKE
    -1.50
     Strokes
    -1.37
     STRO
    -1.33
     stroked
    -1.30
    POSITIVE LOGITS
     of
    0.49
    featureID
    0.49
    Xna
    0.49
     TestBed
    0.47
     protoimpl
    0.47
    matchCondition
    0.46
    ReferenceEquals
    0.43
    IndentedString
    0.43
     and
    0.42
     to
    0.40
    Act Density 0.049%

    No Known Activations