INDEX
    Explanations

    special characters and symbols in the text

    New Auto-Interp
    Negative Logits
    otte
    -0.16
    å¿Ļ
    -0.15
    reed
    -0.14
    ambi
    -0.14
    .Dom
    -0.14
    '<
    -0.14
    oko
    -0.13
     blending
    -0.13
     <$
    -0.13
    ."<
    -0.13
    POSITIVE LOGITS
     close
    0.17
     Close
    0.15
    _close
    0.15
    ardy
    0.15
     Ac
    0.15
     Alive
    0.15
    Ac
    0.15
    close
    0.15
     off
    0.15
    -close
    0.14
    Act Density 0.008%

    No Known Activations