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

    Neuronpedia

    INDEX
    Explanations

    references to ceremonial or traditional practices

    oai_token-act-pair · gpt-3.5-turbo

    references to rituals and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.88
    gets
    -0.82
    clud
    -0.70
     Pik
    -0.68
    onne
    -0.64
    bring
    -0.63
     Kers
    -0.62
    hiro
    -0.61
     Straw
    -0.61
    crop
    -0.61
    POSITIVE LOGITS
     ritual
    1.11
     rituals
    1.10
     rites
    1.07
     Ritual
    1.01
    istically
    0.99
     rite
    0.98
     invocation
    0.86
    itual
    0.85
    aji
    0.84
     ceremonies
    0.83
    Act Density 0.013%

    No Known Activations