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

    Neuronpedia

    INDEX
    Explanations

    references to deliberation or decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    references to decision-making processes and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posted
    -0.60
     Stard
    -0.60
    EMA
    -0.60
    KI
    -0.60
    Claim
    -0.59
    elf
    -0.59
    amy
    -0.57
    olog
    -0.56
    Gy
    -0.56
    ENS
    -0.56
    POSITIVE LOGITS
     deliber
    1.25
     deliberations
    1.04
    itures
    0.73
    itating
    0.71
     debating
    0.71
    atives
    0.70
     chamber
    0.68
     Process
    0.68
    ative
    0.68
    itates
    0.67
    Act Density 0.016%

    No Known Activations