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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

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

    The number "5"

    np_acts-logits-general · gemini-2.0-flash

    five followed by digits/codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Brother
    -0.53
    SBATCH
    -0.53
    awtextra
    -0.52
     Brother
    -0.49
    umumkan
    -0.49
    useEffect
    -0.47
    datac
    -0.47
     brother
    -0.46
     ehrlich
    -0.46
    brother
    -0.46
    POSITIVE LOGITS
    5
    1.55
     fifth
    1.40
     Fifth
    1.35
     five
    1.32
     FIVE
    1.29
    Fifth
    1.24
     Five
    1.20
     FIFTH
    1.19
    ５
    1.16
    five
    1.14
    Act Density 1.243%

    No Known Activations