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

    Neuronpedia

    INDEX
    Explanations

    words related to light or brightness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illumination and light

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-
    -0.79
    Ô
    -0.70
    bid
    -0.68
    士
    -0.65
     Cosponsors
    -0.64
    rentice
    -0.64
     Pact
    -0.63
    ̶
    -0.61
    ¦
    -0.61
    Asset
    -0.61
    POSITIVE LOGITS
    lake
    0.74
    elight
    0.74
     shine
    0.72
     lamps
    0.69
     torches
    0.69
    dark
    0.68
    uther
    0.68
    oshi
    0.67
     candles
    0.67
     dispers
    0.65
    Act Density 0.271%

    No Known Activations