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

    Neuronpedia

    INDEX
    Explanations

    question-based phrases or structures

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

    auxiliary verb questions

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

    whether the text is an interrogative/question (i.e., signals a question being asked).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.64
     autorytatywna
    -0.54
    ViewImports
    -0.51
     $_"
    -0.51
    AccessorTable
    -0.51
     quæ
    -0.49
    cticide
    -0.48
     queſta
    -0.48
    irited
    -0.48
     ſta
    -0.48
    POSITIVE LOGITS
     Waray
    0.39
     Lijst
    0.36
    ContextHolder
    0.35
     AssemblyCulture
    0.35
     invloed
    0.34
     enamorado
    0.34
     behov
    0.33
     entreprise
    0.33
    InfoList
    0.33
     περί
    0.33
    Act Density 0.224%

    No Known Activations