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

    Neuronpedia

    INDEX
    Explanations

    references to or mentions of deities, particularly gods

    oai_token-act-pair · gpt-3.5-turbo

    references to deities or gods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McGr
    -0.77
     Cros
    -0.74
     Lans
    -0.64
    Street
    -0.61
     stitches
    -0.61
    Decre
    -0.60
     Cheong
    -0.60
     Nets
    -0.59
    ogue
    -0.59
    Jen
    -0.59
    POSITIVE LOGITS
    father
    1.36
    mother
    1.20
    parents
    1.15
    esses
    1.03
    frey
    1.03
    sword
    1.01
     worshipped
    1.01
    liness
    1.00
    ess
    0.92
     worship
    0.91
    Act Density 0.046%

    No Known Activations