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

    Neuronpedia

    INDEX
    Explanations

    religious or philosophical concepts and terms

    oai_token-act-pair · gpt-3.5-turbo

    references to various doctrines and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilee
    -0.72
    ells
    -0.72
    bors
    -0.64
    pocket
    -0.63
    arters
    -0.63
    APE
    -0.62
    oÄŁ
    -0.62
    vals
    -0.62
    ilant
    -0.61
    reen
    -0.60
    POSITIVE LOGITS
     doctrine
    1.09
     doctrines
    0.92
     Doctrine
    0.92
    istries
    0.83
    ieu
    0.80
    arium
    0.78
    utical
    0.78
    ologies
    0.74
    ually
    0.73
     orthodoxy
    0.71
    Act Density 0.022%

    No Known Activations