INDEX
    Explanations

    mentions of dairy products and related terminology

    New Auto-Interp
    Negative Logits
    uve
    -0.14
    ilt
    -0.14
    eno
    -0.14
    yte
    -0.14
    reation
    -0.14
    urga
    -0.13
     Elem
    -0.13
    weit
    -0.13
    inha
    -0.13
    ΣΤ
    -0.13
    POSITIVE LOGITS
     ciz
    0.17
    isté
    0.16
    Ģë¡ľ
    0.15
    æķ·
    0.14
    ocab
    0.14
    isay
    0.14
    öst
    0.14
    üb
    0.14
    askan
    0.14
    -animate
    0.13
    Act Density 0.003%

    No Known Activations