INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    continued
    -0.08
    levels
    -0.08
    matic
    -0.08
    minutes
    -0.08
    property
    -0.08
    hein
    -0.08
     realistic
    -0.07
    ív
    -0.07
    -0.07
     plausible
    -0.07
    POSITIVE LOGITS
    -white
    0.15
    0.13
     white
    0.13
    _WHITE
    0.12
     putih
    0.12
    .white
    0.12
     سفید
    0.12
    .WHITE
    0.12
     trắng
    0.12
    .White
    0.11
    Act Density 0.039%

    No Known Activations