INDEX
    Explanations

    words or phrases starting with "So."

    the word "So" used frequently at the beginning of sentences

    New Auto-Interp
    Negative Logits
    .","
    -0.66
     ``(
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
    人
    -0.63
    idity
    -0.63
    "},{"
    -0.62
    "},"
    -0.61
     corresponding
    -0.61
    exclusive
    -0.61
     ``
    -0.60
    POSITIVE LOGITS
    bered
    0.98
    othes
    0.97
    oths
    0.96
    ooo
    0.93
    arin
    0.91
    oooo
    0.91
    oner
    0.90
    fter
    0.89
    aked
    0.86
    apy
    0.85
    Act Density 0.054%

    No Known Activations