INDEX
    Explanations

    punctuation marks, particularly periods

    New Auto-Interp
    Negative Logits
    ä¸ĬãģĴ
    -0.16
    hausen
    -0.15
    oppel
    -0.14
    à¸Ķย
    -0.14
     Svg
    -0.14
    è¼Ŀ
    -0.14
    chet
    -0.14
    /MM
    -0.14
    nik
    -0.13
    LOTS
    -0.13
    POSITIVE LOGITS
    iero
    0.15
    inge
    0.15
     fon
    0.14
     Fus
    0.14
    Nat
    0.14
    wert
    0.14
    batis
    0.14
     Ply
    0.14
    æŁı
    0.14
    ym
    0.14
    Act Density 0.002%

    No Known Activations