INDEX
    Explanations

    references to "Jackson," indicating a focus on a specific individual or location

    New Auto-Interp
    Negative Logits
    UX
    -0.15
    essen
    -0.14
    erta
    -0.14
    /apt
    -0.14
    okies
    -0.14
    610
    -0.14
    oten
    -0.14
     Ñģебе
    -0.14
     ?><
    -0.14
    ux
    -0.14
    POSITIVE LOGITS
     Hole
    0.25
    hole
    0.23
     hole
    0.21
    s
    0.20
    ian
    0.19
    ville
    0.18
    .databind
    0.18
    -hole
    0.17
    sik
    0.17
     Brow
    0.16
    Act Density 0.008%

    No Known Activations