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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements indicative of conversational or written dialogue

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

    foreign language identifiers

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

    The neuron activates on tokens that begin sentences or quoted/parenthetical utterances — i.e., sentence-initial tokens.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.45
    Bereits
    -0.40
    BibitemShut
    -0.36
     ſeveral
    -0.36
     tranſ
    -0.36
     abſ
    -0.35
     также
    -0.35
    stds
    -0.34
     subdivision
    -0.33
    除此之外
    -0.33
    POSITIVE LOGITS
    Personendaten
    0.88
    delwed
    0.82
     beginnetje
    0.68
    httphttps
    0.68
     يتيمه
    0.67
    ReusableCell
    0.66
     betweenstory
    0.65
    verwijspagina
    0.62
     OFDb
    0.61
    AccessorTable
    0.59
    Act Density 0.002%

    No Known Activations