INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    andus
    -0.08
    gf
    -0.08
     Campos
    -0.07
    prud
    -0.07
     spas
    -0.07
     demon
    -0.07
    itters
    -0.07
     Palm
    -0.07
     Lea
    -0.07
    skosten
    -0.07
    POSITIVE LOGITS
    0.13
    0.10
    0.09
     lots
    0.08
    (b
    0.08
    lasting
    0.07
    nem
    0.07
     Lewis
    0.07
    annel
    0.07
    0.07
    Act Density 0.008%

    No Known Activations