INDEX
    Explanations

    references to specific individuals and events in a historical or cultural context

    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    anken
    -0.16
     Ludwig
    -0.16
    ansa
    -0.16
    _WM
    -0.15
     Spi
    -0.15
    cio
    -0.14
    ÅĽcie
    -0.14
    átek
    -0.14
    हन
    -0.14
    POSITIVE LOGITS
    imap
    0.16
    кÑĢÑĭ
    0.16
    ickle
    0.15
    ulum
    0.15
    ëĥ
    0.14
     تاب
    0.14
    pras
    0.14
    èª
    0.14
    æł¡
    0.14
    072
    0.14
    Act Density 0.025%

    No Known Activations