INDEX
    Explanations

    punctuation marks, specifically commas

    New Auto-Interp
    Negative Logits
    iggins
    -0.18
    acho
    -0.16
    rapper
    -0.14
    енÑĤÑĭ
    -0.14
    ials
    -0.14
    zeichnet
    -0.14
    ditor
    -0.14
    ña
    -0.14
    ollah
    -0.14
    ounder
    -0.14
    POSITIVE LOGITS
     pragma
    0.18
    lik
    0.16
    ench
    0.15
    enie
    0.15
    ofi
    0.14
    lob
    0.14
    eos
    0.14
    egal
    0.14
    sett
    0.13
    stock
    0.13
    Act Density 0.018%

    No Known Activations