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

    Neuronpedia

    INDEX
    Explanations

    quotes or dialogue in text

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

    quotation starts

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects opening quotation marks that begin quoted speech or attributed spoken sentences.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    opening quotation marks that signal the start of a direct quote or reported speech.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.64
    AndEndTag
    -0.56
     clés
    -0.47
    ագրություններ
    -0.46
    点此举报
    -0.46
    RTLU
    -0.44
    ganet
    -0.43
    Välislingid
    -0.43
     práci
    -0.42
     généraux
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.59
     Roskov
    0.38
    ymce
    0.37
    futbolista
    0.36
     InputDecoration
    0.35
    SqlQuery
    0.34
    #+#
    0.34
    epam
    0.33
     locomo
    0.32
     reple
    0.31
    Act Density 0.011%

    No Known Activations