INDEX
    Explanations

    the presence of the word "su" in various forms and contexts

    New Auto-Interp
    Negative Logits
    lops
    -0.17
    581
    -0.16
    asters
    -0.16
    oust
    -0.15
    bal
    -0.15
    uchs
    -0.15
    che
    -0.14
     mail
    -0.14
    isers
    -0.14
     Rah
    -0.14
    POSITIVE LOGITS
    icide
    0.25
    icides
    0.23
    arez
    0.22
    eldo
    0.21
    cession
    0.20
    à¹Ģà¸Ľà¸Ńร
    0.19
    nde
    0.19
    veillance
    0.19
    ÑģпÑĸлÑĮ
    0.19
    á»iji
    0.18
    Act Density 0.011%

    No Known Activations