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

    Neuronpedia

    INDEX
    Explanations

    mentions of myths and mythological concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to myths and misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    affer
    -0.82
    foreseen
    -0.81
    perature
    -0.74
    bern
    -0.69
    imentary
    -0.68
    orld
    -0.68
    ells
    -0.67
    ricted
    -0.67
    redd
    -0.67
    eller
    -0.66
    POSITIVE LOGITS
    Myth
    1.19
     Myth
    1.04
     myth
    1.00
    icist
    0.99
     myths
    0.88
    ril
    0.87
    lore
    0.83
     Reincarn
    0.77
     mythology
    0.76
    ic
    0.74
    Act Density 0.013%

    No Known Activations