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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inquiries and responses

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

    phrases related to answering questions and providing assistance

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

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextInputType
    -0.58
    homonymie
    -0.57
     BoxDecoration
    -0.57
    ModelAdmin
    -0.56
     "..\..\
    -0.55
    FromJson
    -0.55
    principalColumn
    -0.55
    ंदीखरीदारी
    -0.53
    pragma
    -0.53
     CanadaChoose
    -0.53
    POSITIVE LOGITS
     questions
    0.82
    Questions
    0.62
     ?'
    0.60
    questions
    0.59
     copious
    0.56
    細かい
    0.55
     Questions
    0.54
     lots
    0.54
    QUESTIONS
    0.53
     detailed
    0.52
    Act Density 0.058%

    No Known Activations