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

    Neuronpedia

    INDEX
    Explanations

    mentions of items or actions related to edible products

    oai_token-act-pair · gpt-3.5-turbo

    references to religious texts and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brance
    -0.77
    abases
    -0.75
     NATO
    -0.73
    AUT
    -0.71
    period
    -0.69
    atorium
    -0.67
    yss
    -0.66
    poll
    -0.66
     Mer
    -0.64
    alg
    -0.63
    POSITIVE LOGITS
    ibles
    1.48
    poons
    0.98
    ible
    0.90
    IBLE
    0.88
    poon
    0.79
    ibility
    0.78
    irtual
    0.78
    uits
    0.76
     veter
    0.75
    ibly
    0.74
    Act Density 0.005%

    No Known Activations