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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and their quantifiers in the context of legal documents

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

    nefarious, remodeling, undercover, sun, available, day, Columbia, 1982–83, I was

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

    the neuron detects numeric tokens and numerical expressions such as dates, times, quantities, amounts, counts, and percentages.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.54
    :✨
    -0.48
     Chwiliwch
    -0.47
    iální
    -0.45
    cshtml
    -0.42
     ویکی‌پدی
    -0.42
     Monteiro
    -0.41
    ècie
    -0.41
     Herrmann
    -0.41
     specific
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    0.51
     Brood
    0.48
     Geſch
    0.45
     ब्रेकडाउन
    0.44
    Diweddarwch
    0.44
     ſeine
    0.44
     dieſer
    0.43
    TokenNameRBRACE
    0.43
     natale
    0.42
    вгений
    0.42
    Act Density 0.127%

    No Known Activations