INDEX
    Explanations

    references to faith and acknowledgment of religious figures

    New Auto-Interp
    Negative Logits
    ikal
    -0.18
    âu
    -0.16
     worsh
    -0.15
    swers
    -0.15
    deen
    -0.15
    _Tis
    -0.15
    -fontawesome
    -0.15
    estroy
    -0.15
    ethoven
    -0.14
    ialog
    -0.14
    POSITIVE LOGITS
     Rog
    0.15
     Nest
    0.15
     Metropolitan
    0.15
    129
    0.14
     Michel
    0.14
     analyzes
    0.14
     Alle
    0.14
    4
    0.14
     Honor
    0.14
    æī¶
    0.14
    Act Density 0.023%

    No Known Activations