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

    Neuronpedia

    INDEX
    Explanations

    first/second person pronouns

    np_max-act · gemini-2.0-flash

    elements related to web development and programming concepts.

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

    The neuron fires on personal pronouns—especially “I” (and to a lesser extent “You” or “It”)—at the start of answer sentences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rians
    -0.06
    τές
    -0.06
    Với
    -0.06
    histor
    -0.06
    ĩnh
    -0.06
    apk
    -0.06
     vero
    -0.06
    Dic
    -0.06
    patient
    -0.06
    шли
    -0.06
    POSITIVE LOGITS
    :s
    0.07
    \Base
    0.07
    (numbers
    0.06
    (depth
    0.06
     snatch
    0.06
    _sign
    0.06
     Голов
    0.06
    Indices
    0.06
     Θ
    0.06
     aşam
    0.06
    Act Density 0.034%

    No Known Activations