INDEX
    Explanations

    references to makeup and beauty products

    New Auto-Interp
    Negative Logits
    soles
    -0.15
    BarItem
    -0.15
    emes
    -0.15
    ifr
    -0.15
    sole
    -0.14
    wit
    -0.14
    idal
    -0.14
    mrt
    -0.14
    wer
    -0.14
    exion
    -0.14
    POSITIVE LOGITS
    _FP
    0.17
    ulp
    0.15
    anine
    0.15
    ichni
    0.14
    ensitive
    0.14
    ause
    0.13
    {{$
    0.13
    obus
    0.13
    anken
    0.13
    γγελ
    0.13
    Act Density 0.007%

    No Known Activations