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

    Neuronpedia

    INDEX
    Explanations

    keywords related to sudden bursts of light or energy

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of the word "flash" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rogens
    -0.85
    ablishment
    -0.84
    essen
    -0.75
    ichick
    -0.71
    yss
    -0.70
    rogen
    -0.69
     Seym
    -0.67
    aepernick
    -0.67
    ally
    -0.67
    awaru
    -0.67
    POSITIVE LOGITS
    lights
    1.18
    bang
    1.10
    cards
    0.96
    fast
    0.91
    ibility
    0.85
    light
    0.83
     flash
    0.81
    flash
    0.80
    lighting
    0.78
    points
    0.77
    Act Density 0.016%

    No Known Activations