INDEX
    Explanations

    references to organized religious structures and affiliations

    New Auto-Interp
    Negative Logits
    adata
    -0.16
    ç§Ģ
    -0.15
    outines
    -0.15
     Beckham
    -0.14
    quoise
    -0.14
    à¤Ĺढ
    -0.14
    licted
    -0.14
     Spartan
    -0.14
    auce
    -0.14
    еÑĢеÑĩ
    -0.14
    POSITIVE LOGITS
     ec
    0.34
     dialogue
    0.32
    /dialog
    0.29
     Dialogue
    0.29
     dialog
    0.29
    dialog
    0.28
     Ec
    0.27
    Dialogue
    0.24
     Dialog
    0.24
    -dialog
    0.24
    Act Density 0.014%

    No Known Activations