INDEX
    Explanations

    names of individuals involved in political and social activism

    New Auto-Interp
    Negative Logits
    comb
    -0.16
     hypers
    -0.15
    lip
    -0.15
     Haskell
    -0.15
    andas
    -0.15
    LEN
    -0.14
    pard
    -0.14
    antha
    -0.14
     reference
    -0.14
    yz
    -0.14
    POSITIVE LOGITS
    aso
    0.15
    ertz
    0.15
     Trad
    0.15
    ÑĥÑī
    0.14
    иÑĢа
    0.14
    oeff
    0.14
    Äĥn
    0.14
    NgModule
    0.14
    İ
    0.14
    ag
    0.13
    Act Density 0.060%

    No Known Activations