INDEX
    Explanations

    punctuation marks, specifically commas

    New Auto-Interp
    Negative Logits
    tec
    -0.17
    .cg
    -0.16
    iese
    -0.16
     fucked
    -0.15
     fucking
    -0.15
    //{{
    -0.15
     Fucking
    -0.14
    isay
    -0.14
    eren
    -0.14
    leur
    -0.14
    POSITIVE LOGITS
    ìĦŃ
    0.15
     Gen
    0.14
    -git
    0.14
     retention
    0.14
     NATO
    0.14
    Ñıк
    0.14
    ï¼Ŀ
    0.14
    ķ
    0.14
     vital
    0.14
     Vital
    0.13
    Act Density 0.000%

    No Known Activations