INDEX
    Explanations

    expressions of surprise or strong emotional reactions

    New Auto-Interp
    Negative Logits
    "]}
    -0.58
     πάντα
    -0.55
    mpt
    -0.54
     ipc
    -0.53
    Дереккөздер
    -0.52
    ultura
    -0.51
    IPC
    -0.51
     ")[
    -0.51
     ')[
    -0.51
    ;}
    -0.51
    POSITIVE LOGITS
    Whoa
    0.79
    ValueStyle
    0.74
     Whoa
    0.69
     yeah
    0.67
    rungsseite
    0.64
    SourceChecksum
    0.64
    uh
    0.64
     wow
    0.63
    CompleteListener
    0.63
    wow
    0.62
    Act Density 0.070%

    No Known Activations