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

    Neuronpedia

    INDEX
    Explanations

    keywords related to candles and candle displays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     refriger
    -0.15
    ãĥĭãĤ¢
    -0.15
    ertools
    -0.15
     dziaÅĤ
    -0.14
    awns
    -0.14
    ework
    -0.14
    _ulong
    -0.14
     бо
    -0.14
     ÙħÙĤ
    -0.13
     belt
    -0.13
    POSITIVE LOGITS
     candle
    0.52
     candles
    0.49
     Candle
    0.47
    wick
    0.34
     wax
    0.33
     Wax
    0.33
     torch
    0.31
     flame
    0.30
     vot
    0.29
     lamp
    0.28
    Act Density 0.026%

    No Known Activations