INDEX
    Explanations

    references to the tone of the text or dialogue

    New Auto-Interp
    Negative Logits
    Rptr
    -0.61
     <",
    -0.57
    InvalidProtocol
    -0.56
     McIntyre
    -0.56
     Atenas
    -0.56
     Øst
    -0.56
    tershire
    -0.55
    featureID
    -0.55
    спубли
    -0.55
     nghề
    -0.54
    POSITIVE LOGITS
     tone
    1.10
    tone
    0.88
     Tone
    0.85
     pipeline
    0.85
    Pipeline
    0.82
    pipeline
    0.82
     Pipeline
    0.81
    Tone
    0.80
     المعيارى
    0.80
     tones
    0.80
    Act Density 0.050%

    No Known Activations