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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash

    references to event tracking and data changes in programming contexts.

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

    The neuron is looking for mentions of “change” (and its inflected forms) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    BIND
    -0.07
    bind
    -0.07
    907
    -0.06
     perspective
    -0.06
    ropol
    -0.06
    	tp
    -0.06
    waters
    -0.06
     venue
    -0.06
     영국
    -0.06
    hol
    -0.06
    POSITIVE LOGITS
    adle
    0.07
    ipse
    0.06
     öğ
    0.06
    .changed
    0.06
     sürede
    0.06
     sow
    0.06
     uttered
    0.06
     Ore
    0.06
     moeten
    0.06
    지노
    0.06
    Act Density 0.017%

    No Known Activations