INDEX
    Explanations

    proper names of people and places

    New Auto-Interp
    Negative Logits
    ulp
    -0.16
     vs
    -0.16
    antee
    -0.15
    Anywhere
    -0.14
    rouw
    -0.14
    locker
    -0.14
    Swift
    -0.13
    ãģªãģı
    -0.13
    ndef
    -0.13
    479
    -0.13
    POSITIVE LOGITS
    oppel
    0.15
    ãĥł
    0.14
     Penis
    0.14
    @js
    0.14
     Thoughts
    0.14
     GSL
    0.14
    atoria
    0.14
    GM
    0.14
    #
    0.14
    apis
    0.13
    Act Density 0.031%

    No Known Activations