INDEX
    Explanations

    website URLs and email addresses

    New Auto-Interp
    Negative Logits
     Seb
    -0.17
    agn
    -0.17
    .Serve
    -0.15
     Fri
    -0.14
    lom
    -0.14
    rio
    -0.14
     éħ
    -0.13
    ponce
    -0.13
    cope
    -0.13
    lad
    -0.13
    POSITIVE LOGITS
    imals
    0.16
    Ïĥο
    0.15
    åīĽ
    0.15
    gii
    0.15
    ollar
    0.15
    ини
    0.14
     Chamber
    0.14
    ÏĥÏī
    0.14
     defaultProps
    0.14
    oving
    0.13
    Act Density 0.032%

    No Known Activations