INDEX
    Explanations

    the presence of the pronoun "I" in various contexts

    New Auto-Interp
    Negative Logits
    ng
    -0.17
    istrovstvÃŃ
    -0.16
    pany
    -0.16
    my
    -0.15
    lier
    -0.15
    ãģªãģĦ
    -0.15
    ils
    -0.15
    irts
    -0.15
     McKenzie
    -0.15
    ne
    -0.14
    POSITIVE LOGITS
     Stam
    0.16
    eum
    0.15
    gle
    0.15
    anela
    0.15
    overy
    0.15
    boxed
    0.14
    BOX
    0.14
    ylland
    0.14
    elts
    0.14
    eft
    0.13
    Act Density 0.112%

    No Known Activations