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

    Neuronpedia

    INDEX
    Explanations

    mentions of sources of light or their characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of "lights."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    via
    -0.71
    ese
    -0.68
    Attempts
    -0.65
    Relations
    -0.65
    clair
    -0.64
     coli
    -0.64
    gress
    -0.63
    ESE
    -0.62
    Interview
    -0.62
     Expression
    -0.61
    POSITIVE LOGITS
    pots
    1.01
     lights
    1.00
     bulb
    0.99
    creen
    0.98
     bulbs
    0.94
    peed
    0.93
    lights
    0.91
    aber
    0.91
    ilver
    0.91
     torches
    0.90
    Act Density 0.009%

    No Known Activations