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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "flash" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to sudden bursts of light or events described as "flash."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rogens
    -0.81
    essen
    -0.77
    ablishment
    -0.76
    ichick
    -0.70
    ally
    -0.69
    romeda
    -0.69
    namese
    -0.69
    yss
    -0.69
    ric
    -0.69
    ŃĶ
    -0.68
    POSITIVE LOGITS
    lights
    1.24
    bang
    1.12
    cards
    0.95
    fast
    0.95
    light
    0.90
    ibility
    0.85
    lighting
    0.83
     flash
    0.81
    flash
    0.81
    points
    0.79
    Act Density 0.026%

    No Known Activations