INDEX
    Explanations

    greetings and well wishes

    exclamatory expressions and greetings

    New Auto-Interp
    Negative Logits
     segreg
    -0.63
     documentaries
    -0.63
     captcha
    -0.62
     controversial
    -0.61
     balk
    -0.60
     subjects
    -0.60
     precip
    -0.60
     omission
    -0.59
    ewitness
    -0.59
     controvers
    -0.59
    POSITIVE LOGITS
    Peace
    1.11
    =-=-=-=-
    1.07
    Happy
    0.96
    Che
    0.96
    Kind
    0.95
    âĻ¥
    0.95
    Thanks
    0.94
    thanks
    0.94
     Merry
    0.93
    xxxxxxxx
    0.93
    Act Density 0.143%

    No Known Activations