INDEX
    Explanations

    references to hair types and hair care

    New Auto-Interp
    Negative Logits
    ÑĤÑĢон
    -0.15
    arth
    -0.15
    .LayoutStyle
    -0.14
     Oliv
    -0.14
    ibold
    -0.14
    ramer
    -0.14
    öl
    -0.14
    ControlEvents
    -0.14
    serrat
    -0.13
    å¸
    -0.13
    POSITIVE LOGITS
     extensions
    0.27
     Extensions
    0.27
    wig
    0.26
     wig
    0.26
    Extensions
    0.26
    extensions
    0.24
    /extensions
    0.23
     Wig
    0.21
     synthetic
    0.21
     extension
    0.19
    Act Density 0.019%

    No Known Activations