INDEX
    Explanations

    phrases indicating contrast or conflict

    New Auto-Interp
    Negative Logits
    mazon
    -0.19
    getSource
    -0.15
    meno
    -0.14
    iddles
    -0.14
     Towers
    -0.14
     mappedBy
    -0.13
    -ignore
    -0.13
    è
    -0.13
    /tos
    -0.13
    intColor
    -0.13
    POSITIVE LOGITS
    ikat
    0.17
    uns
    0.15
    iyon
    0.15
    ãĤ¤ãĥ¤
    0.15
     quarry
    0.15
    chai
    0.14
     Sammy
    0.14
     modest
    0.14
    yre
    0.14
     Pike
    0.14
    Act Density 0.106%

    No Known Activations