INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    <bos>
    -0.85
    ChildScrollView
    -0.61
    клопе
    -0.52
    CloseOperation
    -0.49
    Explicación
    -0.47
    irement
    -0.47
    Famille
    -0.46
     дописавши
    -0.45
    addContainerGap
    -0.45
    OGND
    -0.45
    POSITIVE LOGITS
     déclaration
    0.63
    twimg
    0.57
     الحره
    0.57
    ftagPool
    0.57
    ########.
    0.56
    igshid
    0.55
    fördert
    0.55
    ьаж
    0.55
     Taught
    0.55
    piso
    0.54
    Act Density 0.006%

    No Known Activations