INDEX
    Explanations

    punctuation marks, particularly periods, indicating the end of sentences

    New Auto-Interp
    Negative Logits
    icari
    -0.16
    achs
    -0.16
     ÎķÎĽ
    -0.15
    æľ
    -0.15
    ecial
    -0.14
    familia
    -0.14
    orget
    -0.14
    unj
    -0.14
    orks
    -0.14
    каж
    -0.14
    POSITIVE LOGITS
    oco
    0.15
    usterity
    0.14
    czy
    0.13
     Pick
    0.13
    oren
    0.13
    ometown
    0.13
    ument
    0.13
     Nab
    0.13
    eller
    0.13
     impacted
    0.13
    Act Density 0.108%

    No Known Activations