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

    Neuronpedia

    INDEX
    Explanations

    references to the Pope

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pope and papal authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGHTS
    -0.78
    é¾
    -0.77
    IFE
    -0.77
    terday
    -0.74
    hirt
    -0.74
    nesota
    -0.73
     Wonderland
    -0.71
    ACTED
    -0.70
     Supplemental
    -0.70
    UCT
    -0.69
    POSITIVE LOGITS
    yrus
    1.40
    acy
    1.14
    ular
    1.01
    arella
    1.01
    olitan
    0.98
    agos
    0.98
    oleon
    0.95
    illon
    0.95
    erson
    0.93
    ropri
    0.92
    Act Density 0.024%

    No Known Activations