INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.75
    IGraphics
    -0.75
     AssemblyCulture
    -0.74
    OOTDTY
    -0.72
    OGND
    -0.72
    AccessorTable
    -0.71
     виправивши
    -0.71
    makeConstraints
    -0.71
    ableView
    -0.71
    -------
    -0.70
    POSITIVE LOGITS
     on
    0.75
    <bos>
    0.62
     about
    0.59
     of
    0.58
     that
    0.57
     towards
    0.54
     scuro
    0.52
     or
    0.50
     and
    0.50
     sulla
    0.48
    Act Density 0.014%

    No Known Activations