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

    Neuronpedia

    INDEX
    Explanations

    references to sudden bursts of light or events

    oai_token-act-pair · gpt-3.5-turbo

    references to sudden or striking events, particularly those related to light or rapid occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ablishment
    -0.81
    rogens
    -0.80
    ichick
    -0.74
    essen
    -0.73
    omo
    -0.70
    awaru
    -0.69
    yss
    -0.69
    aepernick
    -0.69
     Colo
    -0.67
    olulu
    -0.67
    POSITIVE LOGITS
    lights
    1.18
    bang
    1.14
     flash
    0.92
    cards
    0.92
    fast
    0.89
    light
    0.86
    flash
    0.84
    lighting
    0.81
    Flash
    0.77
    ibility
    0.76
    Act Density 0.011%

    No Known Activations