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

    Neuronpedia

    INDEX
    Explanations

    envy and admiration

    np_max-act · gemini-2.0-flash

    references to cooking and meal preparation.

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

    This neuron responds to general referencing and explanatory language—especially third‐person pronouns (they, people) and question/explanation words (how, do, make) used in conversational or expository statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     decent
    -0.07
    	board
    -0.07
    ред
    -0.07
    427
    -0.07
    422
    -0.06
    ddie
    -0.06
     Joey
    -0.06
     subscription
    -0.06
    Sun
    -0.06
    conditions
    -0.06
    POSITIVE LOGITS
    .isdigit
    0.07
     Gaut
    0.06
    cmb
    0.06
    teness
    0.06
    .es
    0.06
    λό
    0.06
     diner
    0.06
     тол
    0.06
     quantify
    0.06
    '},
↵
    0.06
    Act Density 0.035%

    No Known Activations