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

    Neuronpedia

    INDEX
    Explanations

    This neuron fires on document‐style headings and metadata labels (e.g. section titles, field names, or other header text).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     releases
    -0.07
     decides
    -0.06
     数
    -0.06
     gọn
    -0.06
     leads
    -0.06
    ('$
    -0.06
     terms
    -0.06
     importantes
    -0.06
     basic
    -0.06
     변수
    -0.06
    POSITIVE LOGITS
     première
    0.07
    olean
    0.07
    دن
    0.07
     Utt
    0.07
     일본
    0.06
     relativ
    0.06
     próximo
    0.06
    .setLayout
    0.06
     cinsel
    0.06
     janvier
    0.06
    Act Density 0.083%

    No Known Activations