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

    Neuronpedia

    INDEX
    Explanations

    references to candles and candle-related imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abel
    -0.17
    sky
    -0.17
    زا
    -0.15
    ame
    -0.14
    exus
    -0.14
     infr
    -0.14
    ÙħاÙĨ
    -0.13
    ultip
    -0.13
    imo
    -0.13
    elly
    -0.13
    POSITIVE LOGITS
    wick
    0.15
    aight
    0.15
     Bernstein
    0.15
    /pl
    0.14
    arium
    0.14
     Cellular
    0.14
    oji
    0.14
    hop
    0.14
    cr
    0.13
    ookie
    0.13
    Act Density 0.002%

    No Known Activations