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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming constructs and functions involving data manipulation

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

    Code or text related to sorting

    np_acts-logits-general · gemini-2.0-flash

    sorting and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fer
    -0.43
     Heinrich
    -0.42
    źć
    -0.42
    craft
    -0.41
    mit
    -0.41
    STROKE
    -0.41
     script
    -0.39
    Enjoying
    -0.39
    gen
    -0.39
    enti
    -0.38
    POSITIVE LOGITS
     sorting
    1.04
     Sorting
    1.03
    Sorting
    0.97
    sorting
    0.91
     SORT
    0.86
     sorted
    0.85
     Sorted
    0.82
    Sort
    0.81
    sort
    0.79
     Sort
    0.79
    Act Density 0.640%

    No Known Activations