INDEX
    Explanations

    titles and roles associated with professionals and public figures

    New Auto-Interp
    Negative Logits
    itled
    -0.17
    Configurer
    -0.16
     Able
    -0.15
    ssf
    -0.15
    hiba
    -0.15
    issen
    -0.14
    stricted
    -0.14
    kker
    -0.14
    imest
    -0.14
    phia
    -0.14
    POSITIVE LOGITS
     best
    0.27
     widely
    0.25
     often
    0.23
    best
    0.23
     based
    0.21
     frequently
    0.21
     better
    0.20
     now
    0.20
     with
    0.20
     long
    0.20
    Act Density 0.121%

    No Known Activations