INDEX
    Explanations

    expressions of admiration and positive sentiment

    New Auto-Interp
    Negative Logits
     ðŁij
    -0.16
     ðŁ
    -0.15
     getParent
    -0.15
    ibia
    -0.15
     ha
    -0.14
     Ha
    -0.14
    StateException
    -0.13
    apt
    -0.13
     Covid
    -0.13
    Ha
    -0.13
    POSITIVE LOGITS
     *__
    0.24
     <
    0.23
     (:
    0.20
    <
    0.19
     GURL
    0.18
    xDD
    0.18
     om
    0.18
     *_
    0.18
    !(:
    0.17
    (:
    0.17
    Act Density 0.072%

    No Known Activations