INDEX
    Explanations

    names of famous actors and celebrities

    names of prominent individuals, particularly actors and their achievements

    New Auto-Interp
    Negative Logits
    sic
    -0.93
    )."
    -0.73
    '."
    -0.68
    .""
    -0.66
    âĵĺ
    -0.66
    .).
    -0.65
    Ire
    -0.65
    .")
    -0.65
    .'"
    -0.59
    espie
    -0.58
    POSITIVE LOGITS
     Doesn
    0.63
     Canaver
    0.63
     Aren
    0.60
    lishes
    0.60
     Isn
    0.60
     Everyday
    0.59
     Groups
    0.59
    '?
    0.58
     Influence
    0.58
     LIMITED
    0.57
    Act Density 0.737%

    No Known Activations