INDEX
    Explanations

    terms related to dumplings or similar food items

    New Auto-Interp
    Negative Logits
    adece
    -0.17
    pard
    -0.17
    bourne
    -0.17
    yonel
    -0.17
    esda
    -0.16
     Sharp
    -0.16
    ²
    -0.16
    istrovstvÃŃ
    -0.16
    anic
    -0.16
    едж
    -0.16
    POSITIVE LOGITS
    mers
    0.22
    blers
    0.20
    pte
    0.19
    bers
    0.19
    ple
    0.18
    pty
    0.17
    bla
    0.17
    plings
    0.17
    be
    0.17
    bral
    0.17
    Act Density 0.038%

    No Known Activations