INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    weiter
    -0.07
    Ball
    -0.07
    -ball
    -0.07
     remainder
    -0.07
    wf
    -0.07
     Observable
    -0.07
    [X
    -0.07
    imu
    -0.07
     difficulty
    -0.07
     Sturm
    -0.07
    POSITIVE LOGITS
     đẹp
    0.12
     belleza
    0.09
     الجميل
    0.09
     aesthetics
    0.09
     peri
    0.09
     schoonheid
    0.09
     красоты
    0.09
    0.08
    0.08
     아름
    0.08
    Act Density 0.003%

    No Known Activations