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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Candle"

    oai_token-act-pair · gpt-3.5-turbo

    references to candles or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.90
    HF
    -0.76
     pity
    -0.69
    ORGE
    -0.67
     ENTER
    -0.66
    FactoryReloaded
    -0.64
    ãĤ´ãĥ³
    -0.63
    FG
    -0.63
    STD
    -0.62
    PUT
    -0.60
    POSITIVE LOGITS
    idates
    1.36
    idate
    1.10
    lest
    1.04
    encies
    0.89
    acies
    0.87
    les
    0.86
    Cand
    0.83
    ice
    0.82
    illo
    0.82
    ulum
    0.82
    Act Density 0.014%

    No Known Activations