INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.47
    daw
    -0.45
     TestBed
    -0.44
     mergeFrom
    -0.41
    numerusform
    -0.41
     nonatomic
    -0.41
    RepeatedField
    -0.40
    WaitGroup
    -0.40
    DialogInterface
    -0.39
    askin
    -0.38
    POSITIVE LOGITS
     style
    0.64
     STYLE
    0.56
     Style
    0.54
    Style
    0.51
     stylu
    0.50
     stylistic
    0.50
     styles
    0.49
    AndEndTag
    0.49
     stijl
    0.47
    style
    0.46
    Act Density 0.005%

    No Known Activations