INDEX
    Explanations

    mentions of the name "Jackson."

    New Auto-Interp
    Negative Logits
    ux
    -0.16
    geh
    -0.16
    UX
    -0.15
    uck
    -0.14
    ager
    -0.14
    essen
    -0.14
    ulen
    -0.14
    ilm
    -0.14
    ustin
    -0.13
    rella
    -0.13
    POSITIVE LOGITS
     Hole
    0.23
    hole
    0.22
    ian
    0.19
     hole
    0.18
    .databind
    0.18
    ville
    0.17
    -hole
    0.17
     EMC
    0.16
    VILLE
    0.16
    croft
    0.16
    Act Density 0.011%

    No Known Activations