INDEX
    Explanations

    expressions of enthusiasm and excitement

    New Auto-Interp
    Negative Logits
    ázev
    -0.15
     Sokol
    -0.15
    /goto
    -0.15
    aday
    -0.15
    anson
    -0.14
    оÑıн
    -0.14
    entine
    -0.14
    è¾
    -0.14
    ambda
    -0.14
    iverz
    -0.14
    POSITIVE LOGITS
     gir
    0.14
    fone
    0.14
    ferred
    0.14
    363
    0.14
    arket
    0.14
     Particip
    0.13
    bread
    0.13
    atic
    0.13
    698
    0.13
     Commons
    0.13
    Act Density 0.015%

    No Known Activations