INDEX
    Explanations

    instances of the term "blob."

    New Auto-Interp
    Negative Logits
    áli
    -0.16
    ska
    -0.16
    sko
    -0.15
    bakan
    -0.15
    iyat
    -0.15
    abel
    -0.15
    iac
    -0.15
    inent
    -0.14
    ails
    -0.14
    allas
    -0.14
    POSITIVE LOGITS
    zych
    0.15
    ileÅŁ
    0.15
    cef
    0.15
    tery
    0.15
    Forge
    0.14
    imd
    0.14
    anford
    0.14
    sey
    0.14
    éļ
    0.13
     liá»ģn
    0.13
    Act Density 0.002%

    No Known Activations