INDEX
    Explanations

    exclamatory punctuation, particularly at the end of sentences

    New Auto-Interp
    Negative Logits
    goods
    -0.15
    IGNED
    -0.15
     Pill
    -0.15
     goods
    -0.14
    coin
    -0.14
    ando
    -0.14
     Goods
    -0.13
    Ế
    -0.13
    oe
    -0.13
    OLON
    -0.13
    POSITIVE LOGITS
     aba
    0.16
     заÑģÑĤ
    0.15
    iac
    0.14
    ATIC
    0.14
    ÑħÑĥ
    0.14
     Ful
    0.14
    æ·
    0.14
     Yardım
    0.13
     opport
    0.13
    ole
    0.13
    Act Density 0.009%

    No Known Activations