INDEX
    Explanations

    mentions of relationships and connections between people or groups

    "with" followed by "whom" or related words

    New Auto-Interp
    Negative Logits
     مشين
    -0.93
    IsContent
    -0.86
    DoubleQuotes
    -0.82
    WebVitals
    -0.79
    itself
    -0.79
     виправивши
    -0.77
    OGND
    -0.76
    TypedDataSet
    -0.76
    ModelSerializer
    -0.76
    AccessorTable
    -0.75
    POSITIVE LOGITS
     whom
    0.78
     who
    0.78
     or
    0.63
    whom
    0.57
     którzy
    0.53
     whose
    0.52
    或者
    0.52
    あるいは
    0.52
    거나
    0.51
    who
    0.50
    Act Density 0.695%

    No Known Activations