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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the digit “4,” particularly as part of references to “GPT-4.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Techniques
    -0.06
     lest
    -0.06
     rhs
    -0.06
    Patients
    -0.06
     patients
    -0.06
    ën
    -0.06
    _bb
    -0.06
     Queen
    -0.06
    (line
    -0.06
    Initializer
    -0.06
    POSITIVE LOGITS
     momentos
    0.08
     mountains
    0.07
     chuck
    0.07
     ràng
    0.06
    哪
    0.06
     Shaman
    0.06
    neas
    0.06
     modne
    0.06
    isha
    0.06
    -nav
    0.06
    Act Density 0.002%

    No Known Activations