INDEX
    Explanations

    dimensions related to graphical or layout elements

    New Auto-Interp
    Negative Logits
    LookAnd
    -0.79
    Personendaten
    -0.66
     Beſ
    -0.64
     Watch
    -0.62
     Theſe
    -0.62
    Personensuche
    -0.61
     blumen
    -0.59
    abestanden
    -0.59
    Izvori
    -0.58
    IsMutable
    -0.58
    POSITIVE LOGITS
    Size
    1.59
     Size
    1.45
     size
    1.19
     SIZE
    1.14
    SIZE
    1.08
    size
    1.05
     Größe
    0.85
     Sizes
    0.84
     sizes
    0.78
    サイズ
    0.76
    Act Density 0.011%

    No Known Activations