INDEX
    Explanations

    mentions of hair-related services and businesses

    New Auto-Interp
    Negative Logits
    먹
    -0.15
    urdy
    -0.14
    gota
    -0.13
    addock
    -0.13
    ança
    -0.13
    بط
    -0.13
     cánh
    -0.13
    deploy
    -0.13
    dek
    -0.12
     deploy
    -0.12
    POSITIVE LOGITS
     salon
    0.54
     hairst
    0.50
     Salon
    0.49
     hair
    0.48
     Hair
    0.46
     Hairst
    0.44
     haircut
    0.44
     stylist
    0.43
    Hair
    0.43
     hairstyle
    0.42
    Act Density 0.112%

    No Known Activations