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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and contextual phrases indicating relationships or conditions in a narrative

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

    lists like where, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BROOK
    -0.34
     émer
    -0.34
    rfloor
    -0.34
     Mulher
    -0.33
    뀜
    -0.31
     bereit
    -0.31
    young
    -0.31
     YOUNG
    -0.31
    volt
    -0.30
     hostage
    -0.30
    POSITIVE LOGITS
     nahilalakip
    0.79
    setupUi
    0.66
     FetchType
    0.58
     disponibilités
    0.58
    ReusableCell
    0.55
     snippetHide
    0.54
    SOUNDBITE
    0.53
    ImageContext
    0.52
    NameInMap
    0.52
     cherchés
    0.52
    Act Density 0.064%

    No Known Activations