INDEX
    Explanations

    expressions of emotions or reactions, particularly those that are exuberant or emphasize strong sentiments

    New Auto-Interp
    Negative Logits
    Oh
    -0.35
     really
    -0.33
     honestly
    -0.33
     anyway
    -0.32
     Oh
    -0.31
    Tbh
    -0.31
    -0.31
     tbh
    -0.30
     ressemble
    -0.30
    本当に
    -0.30
    POSITIVE LOGITS
     Chwiliwch
    0.68
     ब्रेकडाउन
    0.66
     Yay
    0.66
    principalColumn
    0.65
     nakalista
    0.63
    Cue
    0.62
     yay
    0.61
    parsedMessage
    0.61
    BOOM
    0.60
     BOOM
    0.60
    Act Density 0.293%

    No Known Activations