INDEX
    Explanations

    mentions of the word "Florence."

    New Auto-Interp
    Negative Logits
    lings
    -0.17
    res
    -0.15
    ere
    -0.14
     McCabe
    -0.14
    esimal
    -0.14
    reland
    -0.14
    nof
    -0.14
    rep
    -0.13
    eniable
    -0.13
    ichi
    -0.13
    POSITIVE LOGITS
    ī
    0.17
     Bened
    0.15
    _IPV
    0.15
    лада
    0.14
    umed
    0.14
    ży
    0.14
    pth
    0.14
     Trident
    0.13
    umpt
    0.13
     Verg
    0.13
    Act Density 0.010%

    No Known Activations