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

    Neuronpedia

    INDEX
    Explanations

    content related to decision-making challenges and game theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     throat
    -0.14
    eten
    -0.14
     prim
    -0.14
    EIF
    -0.14
    pte
    -0.13
     Ze
    -0.13
     maker
    -0.13
    nore
    -0.13
    azzi
    -0.13
     ak
    -0.13
    POSITIVE LOGITS
    orado
    0.16
    ogi
    0.16
    azor
    0.15
     tasks
    0.15
    printStats
    0.14
    curity
    0.14
    /lg
    0.14
    ERAL
    0.14
    tasks
    0.14
    enstvÃŃ
    0.14
    Act Density 0.021%

    No Known Activations