INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     aerobic
    -0.08
    /activity
    -0.07
     analges
    -0.07
     younger
    -0.07
     brownie
    -0.07
     youth
    -0.07
    Youth
    -0.07
     point
    -0.07
     Youth
    -0.07
    err
    -0.07
    POSITIVE LOGITS
     widths
    0.15
     Width
    0.13
    Widths
    0.13
    	width
    0.13
    _width
    0.12
     width
    0.12
    (width
    0.12
     largura
    0.12
     largeur
    0.12
    _WIDTH
    0.12
    Act Density 0.003%

    No Known Activations