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

    Neuronpedia

    INDEX
    Explanations

    Pronouns and quotations

    np_max-act · gemini-2.0-flash

    conversational context and inquiries related to support and assistance.

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

    The neuron specializes in detecting first‐person pronouns and self‐references (e.g. “I,” “me,” “my,” “first person”) indicating the speaker referring to themselves.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     roses
    -0.07
    Lewis
    -0.07
     Abbas
    -0.06
     respondent
    -0.06
     terror
    -0.06
     γ
    -0.06
     dancer
    -0.06
    婚
    -0.06
    За
    -0.06
     flyers
    -0.06
    POSITIVE LOGITS
    =sc
    0.07
    gency
    0.06
     programa
    0.06
    .getItemId
    0.06
    getAs
    0.06
     currentPosition
    0.06
    .sc
    0.06
    162
    0.06
     vẻ
    0.06
     потрап
    0.06
    Act Density 0.017%

    No Known Activations