INDEX
    Explanations

    conjunctions and transition phrases that indicate contrast or continuation in discourse

    New Auto-Interp
    Negative Logits
    igin
    -0.17
    ique
    -0.16
    ic
    -0.15
    ieval
    -0.15
    eral
    -0.15
    iego
    -0.15
    ipe
    -0.14
    nbsp
    -0.14
    ically
    -0.14
    ilton
    -0.14
    POSITIVE LOGITS
    @student
    0.18
    drawing
    0.15
    Ñĥй
    0.14
    erialized
    0.13
    .onerror
    0.13
     EZ
    0.13
    onis
    0.13
    ī´
    0.13
    areth
    0.13
    lesen
    0.12
    Act Density 0.190%

    No Known Activations