INDEX
    Explanations

    phrases related to a person named Luke

    mentions of the name "Luke."

    New Auto-Interp
    Negative Logits
    ãĤ¢ãĥ«
    -0.87
    ursed
    -0.85
    Ö¼
    -0.75
    itect
    -0.70
    Ú
    -0.70
    uration
    -0.70
    Ùħ
    -0.70
    ãĤ¡
    -0.69
    ifice
    -0.69
    ktop
    -0.69
    POSITIVE LOGITS
     Skywalker
    1.55
    warm
    1.40
     Cage
    1.10
     Vader
    0.90
    lihood
    0.85
     Luke
    0.85
     Lans
    0.79
    avin
    0.78
     Gat
    0.77
    film
    0.76
    Act Density 0.009%

    No Known Activations