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

    Neuronpedia

    INDEX
    Explanations

    references to light sources

    oai_token-act-pair · gpt-3.5-turbo

    references to lights and lighting conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llah
    -0.92
    urdue
    -0.78
    cific
    -0.70
    abama
    -0.69
    ctive
    -0.69
    clusive
    -0.68
    utical
    -0.67
    arenthood
    -0.66
    ppo
    -0.65
    cture
    -0.65
    POSITIVE LOGITS
     bulb
    1.10
     bulbs
    1.00
    lights
    0.97
     lights
    0.94
     emitting
    0.92
    pots
    0.89
    aber
    0.87
    peed
    0.86
     blinking
    0.85
     flashing
    0.85
    Act Density 0.028%

    No Known Activations