INDEX
    Explanations

    activations related to facial cleansers and makeup remover

    references to the state of Illinois

    New Auto-Interp
    Negative Logits
     pist
    -0.71
     Schne
    -0.67
     Betty
    -0.67
    aterasu
    -0.62
     square
    -0.62
     Pist
    -0.61
     Hend
    -0.60
     antiquity
    -0.60
     dec
    -0.60
     reasonably
    -0.59
    POSITIVE LOGITS
    IL
    4.14
    ILS
    2.96
    ILE
    2.12
    ils
    2.10
    il
    2.05
    ILA
    1.94
    ILD
    1.77
    iles
    1.74
    iling
    1.68
    ile
    1.63
    Act Density 0.011%

    No Known Activations