INDEX
    Explanations

    expressions of frustration or dissatisfaction

    New Auto-Interp
    Negative Logits
    stav
    -0.15
    ofilm
    -0.15
    oker
    -0.14
    κά
    -0.14
    ippi
    -0.14
    orted
    -0.14
    åķª
    -0.14
    åłĤ
    -0.14
     Wow
    -0.13
    hei
    -0.13
    POSITIVE LOGITS
     ARG
    0.30
     ble
    0.29
     U
    0.25
    ugh
    0.25
    ARG
    0.25
     ACK
    0.25
     sigh
    0.24
     u
    0.24
     ur
    0.23
     Bah
    0.23
    Act Density 0.198%

    No Known Activations