Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to deities or divine figures

    oai_token-act-pair · gpt-3.5-turbo

    references to gods or deities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ospons
    -0.64
    20439
    -0.64
     Inspection
    -0.64
     McCorm
    -0.64
     McInt
    -0.64
     Photo
    -0.63
    orter
    -0.62
     Scotia
    -0.62
     Newsweek
    -0.62
    romy
    -0.62
    POSITIVE LOGITS
     gods
    3.56
     Gods
    3.48
     deities
    2.37
     god
    1.67
     deity
    1.63
     goddess
    1.59
     idols
    1.47
     heavens
    1.47
    god
    1.45
     Goddess
    1.37
    Act Density 0.014%

    No Known Activations