INDEX
    Explanations

    occurrences of the word "killer" in various contexts

    New Auto-Interp
    Negative Logits
    orial
    -0.19
    ecies
    -0.16
    ãĤīãģļ
    -0.16
    isters
    -0.15
    ÙĪÙĦد
    -0.14
    flip
    -0.14
     Gan
    -0.14
    izzer
    -0.14
    anity
    -0.14
     Aerospace
    -0.14
    POSITIVE LOGITS
    rips
    0.16
    ulous
    0.15
     Wich
    0.14
    çļĦæĺ¯
    0.14
    eras
    0.14
    ucs
    0.14
     stalking
    0.14
    erm
    0.14
    throw
    0.13
    aa
    0.13
    Act Density 0.006%

    No Known Activations