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

    Neuronpedia

    INDEX
    Explanations

    references to religious or sacred terminology

    oai_token-act-pair · gpt-3.5-turbo

    the term "Holy" and its variations, indicating a focus on religious concepts or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.88
    atown
    -0.87
    PsyNetMessage
    -0.82
    yrinth
    -0.79
    ickr
    -0.79
    Downloadha
    -0.73
    ļéĨĴ
    -0.71
    wana
    -0.71
    apses
    -0.70
    xual
    -0.70
    POSITIVE LOGITS
     Grail
    1.02
     Scripture
    0.81
    father
    0.78
     Trinity
    0.77
     Father
    0.73
     gra
    0.73
     smokes
    0.72
    field
    0.71
     Maiden
    0.70
     Scriptures
    0.69
    Act Density 0.016%

    No Known Activations