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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal or authoritative requirements

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of mandates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istics
    -0.86
    luaj
    -0.78
    sam
    -0.75
     Sul
    -0.74
    encers
    -0.71
    uni
    -0.70
    Sem
    -0.69
    Sus
    -0.69
    ãģį
    -0.69
    stocks
    -0.68
    POSITIVE LOGITS
     mandate
    1.11
     mandates
    0.87
    FontSize
    0.83
     mandated
    0.82
     compel
    0.81
    awaru
    0.81
     creep
    0.79
     imposed
    0.77
    qqa
    0.74
    jriwal
    0.74
    Act Density 0.010%

    No Known Activations