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

    Neuronpedia

    INDEX
    Explanations

    terms related to religious or philosophical beliefs and teachings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "doctrine" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ells
    -0.77
    Õ
    -0.67
    aged
    -0.67
    APE
    -0.67
    vals
    -0.66
    bors
    -0.65
    ilee
    -0.63
    ilant
    -0.63
    athy
    -0.62
    Occup
    -0.61
    POSITIVE LOGITS
     doctrine
    1.11
     doctrines
    0.95
    ologies
    0.85
     Doctrine
    0.83
    arium
    0.81
     dictates
    0.80
     underpin
    0.78
     dogma
    0.75
     orthodoxy
    0.74
     teachings
    0.73
    Act Density 0.029%

    No Known Activations