INDEX
    Explanations

    references to beauty products, especially makeup

    references to makeup and cosmetics

    New Auto-Interp
    Negative Logits
    awar
    -0.77
    ollow
    -0.73
    âķIJâķIJ
    -0.72
    Fal
    -0.71
    ARR
    -0.70
     Hammond
    -0.69
     Chronicle
    -0.67
    imov
    -0.66
    DEM
    -0.66
    sent
    -0.66
    POSITIVE LOGITS
     makeup
    1.14
     brushes
    0.82
     shader
    0.77
    ipedia
    0.76
     wardrobe
    0.76
     pedals
    0.75
     artist
    0.74
     wig
    0.74
     cosmetics
    0.73
    ates
    0.73
    Act Density 0.011%

    No Known Activations