INDEX
    Explanations

    instances of dialogue and conversational elements

    New Auto-Interp
    Negative Logits
    ÑĢеÑģ
    -0.14
    affen
    -0.14
    ãĥ¼ãĥģ
    -0.14
    ãĥ³ãĥIJãĥ¼
    -0.13
    509
    -0.13
    mÃŃt
    -0.13
    اÙĩÙħ
    -0.13
    zp
    -0.13
    ergarten
    -0.13
    ackson
    -0.13
    POSITIVE LOGITS
     notice
    0.43
     noticing
    0.40
     notices
    0.39
     noticed
    0.39
    noticed
    0.35
     Notice
    0.33
    notice
    0.32
     hear
    0.30
    Notice
    0.30
     see
    0.29
    Act Density 0.317%

    No Known Activations