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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash

    JavaScript code that utilizes the OpenAI API for generating responses based on user input.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on code references to the OpenAI client and its model specification (e.g. “openai,” “GPT,” “model_name,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cloned
    -0.06
    拔
    -0.06
     EVENT
    -0.06
    .sa
    -0.06
     villa
    -0.06
     giants
    -0.06
    Ops
    -0.06
     Sorted
    -0.06
    dale
    -0.06
    pp
    -0.06
    POSITIVE LOGITS
    'name
    0.07
     irreversible
    0.06
    Sab
    0.06
     Mesa
    0.06
     Sgt
    0.06
    編
    0.06
     userDao
    0.06
     ("-
    0.06
    ephir
    0.06
    lassian
    0.06
    Act Density 0.011%

    No Known Activations