INDEX
    Explanations

    punctuation and common structural elements in written text

    New Auto-Interp
    Negative Logits
    DataURL
    -0.15
     Vog
    -0.15
    iten
    -0.15
    ist
    -0.14
    ØŃÙĩ
    -0.14
    .translate
    -0.14
    News
    -0.14
    lisi
    -0.14
    ÃĨ
    -0.14
    oud
    -0.14
    POSITIVE LOGITS
    jie
    0.18
    ìħĢ
    0.16
    uffman
    0.16
    rell
    0.15
    pf
    0.15
     Platt
    0.15
    ska
    0.15
    ce
    0.14
    eper
    0.14
    ÑĨеÑĢ
    0.14
    Act Density 0.016%

    No Known Activations