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

    Neuronpedia

    INDEX
    Explanations

    mentions of Popes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Pope

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agents
    -0.73
    agent
    -0.68
    iries
    -0.66
    dat
    -0.64
     segreg
    -0.62
     engineering
    -0.61
     competitive
    -0.60
     lan
    -0.60
     milliseconds
    -0.58
     sustain
    -0.58
    POSITIVE LOGITS
    Pope
    3.77
     Pope
    3.69
     pope
    2.85
     Vatican
    2.08
     Archbishop
    1.88
    atican
    1.80
     pont
    1.79
     Catholics
    1.78
     Cardinal
    1.76
     Catholicism
    1.63
    Act Density 0.017%

    No Known Activations