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

    Neuronpedia

    INDEX
    Explanations

    words related to sudden bursts of light or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flash" and its variations, indicating a focus on sudden occurrences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rogens
    -0.76
    ablishment
    -0.75
    ordan
    -0.73
    omo
    -0.70
    essen
    -0.69
     Colo
    -0.69
     Valkyrie
    -0.68
    chen
    -0.66
    olulu
    -0.66
    quartered
    -0.66
    POSITIVE LOGITS
    lights
    1.21
     flash
    1.07
    bang
    1.05
    flash
    0.97
    cards
    0.88
    Flash
    0.88
     lights
    0.85
    light
    0.83
    lighting
    0.83
    fast
    0.83
    Act Density 0.008%

    No Known Activations