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

    Neuronpedia

    INDEX
    Explanations

    instances where specific subjects and actions are discussed in a context involving responsibility or actions taken

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

    taken together

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

    The neuron detects sentence- or clause-initial capitalized content words (tokens that begin sentences, headings, or major clause transitions).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     preſent
    -0.52
     paſſ
    -0.49
     ſta
    -0.48
    ↵↵
    -0.48
     Perſ
    -0.47
     ſtre
    -0.47
    ″]
    -0.47
     ſen
    -0.47
     laſt
    -0.47
     viſ
    -0.46
    POSITIVE LOGITS
     EClass
    0.57
    principalColumn
    0.50
    setContentView
    0.50
    ParallelGroup
    0.49
     يتيمه
    0.48
    ----</
    0.47
    XmlAccessorType
    0.45
     propOrder
    0.45
    CloseOperation
    0.44
    sizeCache
    0.43
    Act Density 2.120%

    No Known Activations