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

    Neuronpedia

    INDEX
    Explanations

    the word stems "atur" (e.g., "nature", "saturated") and variations of this stem

    oai_token-act-pair · gpt-3.5-turbo

    variations of the root word "saturate."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSpecialOrderable
    -0.67
     awoken
    -0.67
    Sil
    -0.66
    Wan
    -0.65
    ICES
    -0.65
    ĪĴ
    -0.62
     edible
    -0.61
    doms
    -0.60
    hood
    -0.59
    communications
    -0.57
    POSITIVE LOGITS
    anism
    0.93
    tarian
    0.90
    tarians
    0.90
    isen
    0.89
    als
    0.88
    aling
    0.87
    ificent
    0.86
    aton
    0.86
    adian
    0.86
    acular
    0.85
    Act Density 0.021%

    No Known Activations