INDEX
    Explanations

    the preposition "on," particularly in contexts related to sources of information

    New Auto-Interp
    Negative Logits
    ature
    -0.74
    rolet
    -0.67
    soDeliveryDate
    -0.65
    Pie
    -0.64
    pid
    -0.64
    apolis
    -0.64
    idia
    -0.63
    figure
    -0.63
    olphin
    -0.61
    pire
    -0.61
    POSITIVE LOGITS
     condition
    0.76
    anism
    0.76
     sidelines
    0.72
     Flan
    0.64
     Ens
    0.58
     beh
    0.58
    psc
    0.58
    fully
    0.57
     downs
    0.57
    icia
    0.56
    Act Density 0.050%

    No Known Activations