INDEX
    Explanations

    _phrases indicating a strong opinion or judgment._

    phrases that convey the act of stating or expressing thoughts

    New Auto-Interp
    Negative Logits
    panic
    -0.65
    ascript
    -0.62
     notebook
    -0.61
     Frie
    -0.59
    catentry
    -0.59
    fram
    -0.58
     infl
    -0.58
    ty
    -0.57
    aspx
    -0.56
     captcha
    -0.54
    POSITIVE LOGITS
     goodbye
    0.97
     nothing
    0.97
     farewell
    0.78
    nothing
    0.70
    INGS
    0.68
     aloud
    0.67
    hern
    0.67
     hello
    0.66
    hem
    0.65
     Goodbye
    0.65
    Act Density 0.056%

    No Known Activations