INDEX
    Explanations

    references to the name "Jackson" and its variations

    New Auto-Interp
    Negative Logits
    geh
    -0.15
    ux
    -0.14
    uck
    -0.14
    essen
    -0.14
    én
    -0.13
    erta
    -0.13
    rella
    -0.13
    iability
    -0.13
    utar
    -0.13
    tit
    -0.13
    POSITIVE LOGITS
    hole
    0.19
    croft
    0.18
     Hole
    0.17
    ville
    0.17
    VILLE
    0.17
    .databind
    0.17
    avel
    0.15
     Benny
    0.15
    rabbit
    0.15
    ian
    0.15
    Act Density 0.013%

    No Known Activations