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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and structure, particularly involving programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    885
    -0.15
    BOOLE
    -0.15
     timelines
    -0.15
    isnan
    -0.14
    unan
    -0.13
     Hour
    -0.13
    à¸ģà¸ķ
    -0.13
    usra
    -0.12
     VOID
    -0.12
     timings
    -0.12
    POSITIVE LOGITS
     num
    0.36
     size
    0.36
    size
    0.32
     count
    0.32
     max
    0.30
    .size
    0.30
     Size
    0.29
    =size
    0.28
     total
    0.28
    num
    0.28
    Act Density 0.417%

    No Known Activations