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

    Neuronpedia

    INDEX
    Explanations

    references to religious or sacred places, especially temples

    oai_token-act-pair · gpt-3.5-turbo

    references to places of worship, specifically temples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.69
    ÑĮ
    -0.68
     Barkley
    -0.67
    leneck
    -0.67
    ives
    -0.65
     Kessler
    -0.64
    Published
    -0.63
     Jenner
    -0.63
    ãģį
    -0.63
    DOS
    -0.62
    POSITIVE LOGITS
     temple
    1.10
     temples
    1.02
     altar
    0.89
     ceremonies
    0.87
    inence
    0.84
     maiden
    0.84
    mage
    0.82
    plates
    0.79
     shrine
    0.79
     ceremony
    0.77
    Act Density 0.013%

    No Known Activations