INDEX
    Explanations

    attributes related to text and background styling in UI layouts

    New Auto-Interp
    Negative Logits
    akh
    -0.17
    isse
    -0.16
    czy
    -0.15
    _simps
    -0.15
     relative
    -0.15
     Kil
    -0.15
     Blasio
    -0.15
    bies
    -0.14
    andi
    -0.14
    rend
    -0.13
    POSITIVE LOGITS
    Reviewed
    0.15
    ouv
    0.15
    ëĿ¼ëıĦ
    0.15
    ieri
    0.15
    artz
    0.15
    nout
    0.15
     Sabb
    0.14
    YL
    0.14
    auer
    0.14
    olk
    0.14
    Act Density 0.002%

    No Known Activations