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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    words related to historical military events and personal relationships.

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

    This neuron activates on the third‐person plural pronoun “they.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Locke
    -0.07
     доч
    -0.06
     indul
    -0.06
    rozen
    -0.06
     restaurant
    -0.06
    "We
    -0.06
     حف
    -0.06
    okens
    -0.06
     RTE
    -0.06
     Labs
    -0.06
    POSITIVE LOGITS
     carbon
    0.07
     semiclassical
    0.07
    patient
    0.06
    /host
    0.06
     فرهنگی
    0.06
    _Util
    0.06
    _Val
    0.06
    няют
    0.06
     dto
    0.06
    敗
    0.06
    Act Density 0.125%

    No Known Activations