INDEX
    Explanations

    phrases or terms related to places of worship, specifically churches

    references to the concept of "church."

    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.71
     neurot
    -0.68
     "$:/
    -0.64
     Yak
    -0.63
     Rog
    -0.63
    nir
    -0.61
    à¸
    -0.61
    LER
    -0.61
     Paste
    -0.61
    ï¸ı
    -0.61
    POSITIVE LOGITS
    goers
    1.19
    yard
    1.18
    yards
    0.98
    esan
    0.97
     choir
    0.88
    going
    0.88
     bells
    0.87
     Patriarch
    0.87
     fathers
    0.86
    fires
    0.86
    Act Density 0.023%

    No Known Activations