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

    Neuronpedia

    INDEX
    Explanations

    references to lights or lighting

    oai_token-act-pair · gpt-3.5-turbo

    references to lighting conditions or types of illumination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etta
    -0.62
     transfer
    -0.61
     fragment
    -0.61
     invade
    -0.57
     ally
    -0.57
     Cu
    -0.57
     base
    -0.56
     Store
    -0.56
     Gulf
    -0.55
    itte
    -0.55
    POSITIVE LOGITS
    lights
    4.78
    lighting
    2.47
    light
    1.89
     lights
    1.53
     Lights
    1.31
    fires
    1.19
    waters
    1.18
     lamps
    1.16
     headlights
    1.07
    lines
    1.05
    Act Density 0.011%

    No Known Activations