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

    Neuronpedia

    INDEX
    Explanations

    topics related to health, wellness, and safety regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocket
    -0.16
    AndGet
    -0.14
    á»Ļ
    -0.14
    cons
    -0.13
    SEL
    -0.13
    Drawer
    -0.13
    cket
    -0.13
    353
    -0.13
     Doe
    -0.13
    trim
    -0.13
    POSITIVE LOGITS
    rate
    0.15
     Freed
    0.15
    noop
    0.15
    raquo
    0.15
    ihan
    0.15
    haus
    0.14
    cw
    0.14
    dorf
    0.14
    anos
    0.14
    WB
    0.13
    Act Density 0.061%

    No Known Activations