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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash

    conversational dynamics involving taboo topics or fantasies.

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

    This neuron detects tokens that occur in quoted or spoken dialogue (i.e. inside quotation marks or speaker turns).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     redesign
    -0.07
     Millennium
    -0.06
    очных
    -0.06
     Offensive
    -0.06
    Stars
    -0.06
    409
    -0.06
     ketogenic
    -0.06
     Sands
    -0.06
     formatter
    -0.06
    .getProperty
    -0.06
    POSITIVE LOGITS
     LO
    0.07
    PP
    0.07
     AN
    0.07
     dahi
    0.06
     eater
    0.06
    _TIMES
    0.06
    _pel
    0.06
    imedia
    0.06
     GNUNET
    0.06
     procrast
    0.06
    Act Density 0.111%

    No Known Activations