INDEX
    Explanations

    rhetorical questions or clauses

    Questions and exclamations

    New Auto-Interp
    Negative Logits
    vacy
    -0.57
    H
    -0.56
     Antony
    -0.51
     Rady
    -0.48
    _
    -0.48
    X
    -0.47
     inf
    -0.47
    =
    -0.46
     =
    -0.46
    PSC
    -0.46
    POSITIVE LOGITS
    )”.
    1.13
    IntoConstraints
    1.11
    <bos>
    1.09
    .)}
    1.08
     myſelf
    1.05
    antaranya
    1.03
    ."));
    1.03
    .”)
    1.03
     disambiguazione
    1.02
     كومونز
    1.02
    Act Density 0.940%

    No Known Activations