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

    Neuronpedia

    INDEX
    Explanations

    references to data structures, specifically tuples

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

    tuples and tuple sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EnglishChoose
    -0.42
    原始内容存档于
    -0.39
    [++
    -0.38
     saja
    -0.35
    NFS
    -0.34
    '}>
    -0.34
     Wigan
    -0.34
     Marien
    -0.33
    Cys
    -0.33
    specialchars
    -0.32
    POSITIVE LOGITS
     Tuple
    2.73
    Tuple
    2.42
     tuple
    0.92
     tuples
    0.92
    uples
    0.81
    tup
    0.75
    tuples
    0.72
     tup
    0.67
    Tup
    0.65
    tuple
    0.65
    Act Density 0.002%

    No Known Activations