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

    Neuronpedia

    INDEX
    Explanations

    references to religious concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to religious themes and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lans
    -0.99
    agher
    -0.89
    ufact
    -0.88
    20439
    -0.87
     Tunnel
    -0.80
    iard
    -0.71
    aunder
    -0.70
    æ©
    -0.69
    hoe
    -0.69
     Shed
    -0.68
    POSITIVE LOGITS
     affili
    1.03
     affiliation
    0.99
     beliefs
    0.94
     fundamental
    0.92
     liberty
    0.91
     zeal
    0.90
     ferv
    0.89
     freedom
    0.88
     liberties
    0.88
     dogma
    0.88
    Act Density 0.030%

    No Known Activations