INDEX
    Explanations

    variations of the word "shoe."

    New Auto-Interp
    Negative Logits
    uros
    -0.17
    avers
    -0.17
    uyen
    -0.16
    ään
    -0.15
    Äĥr
    -0.15
    ufs
    -0.15
    usic
    -0.14
    ạm
    -0.14
     Bron
    -0.14
    bare
    -0.14
    POSITIVE LOGITS
    emaker
    0.32
    oled
    0.22
    estring
    0.21
    enstein
    0.19
    onya
    0.18
    chwitz
    0.18
    enthal
    0.18
    enef
    0.18
    field
    0.18
    ettle
    0.17
    Act Density 0.007%

    No Known Activations