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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and dialogue indicators in the text

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

    quotation marks and its content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.86
    contentLoaded
    -0.74
    rungsseite
    -0.73
    AsUp
    -0.72
    Personendaten
    -0.71
    CloseOperation
    -0.71
    NameInMap
    -0.64
    -0.63
    InputBorder
    -0.62
    MemoryWarning
    -0.61
    POSITIVE LOGITS
    ̣i
    0.39
    strip
    0.35
    िला
    0.32
    Intro
    0.32
    Abu
    0.32
    I
    0.32
     Instagram
    0.32
     Abu
    0.31
    byte
    0.31
    Unit
    0.31
    Act Density 0.010%

    No Known Activations