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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing rules

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -1.09
    igated
    -0.83
    issance
    -0.73
    assador
    -0.68
    rial
    -0.67
    merce
    -0.67
    ienced
    -0.67
    attled
    -0.67
    leased
    -0.67
     Cros
    -0.66
    POSITIVE LOGITS
     governing
    0.82
    breakers
    0.81
     lawy
    0.79
    witz
    0.79
    ULE
    0.77
    breaker
    0.76
     violations
    0.74
    Rule
    0.74
     dictate
    0.73
    book
    0.72
    Act Density 0.029%

    No Known Activations