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

    Neuronpedia

    INDEX
    Explanations

    references to chilling or soaking times in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hours and overnight periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.86
    transQ
    -0.65
    orianCalendar
    -0.65
     propOrder
    -0.64
    发表于
    -0.64
    -------
    -0.62
     ſeine
    -0.62
     ddelwed
    -0.62
    utives
    -0.61
     Administrativna
    -0.61
    POSITIVE LOGITS
     overnight
    0.50
     Overnight
    0.39
     hours
    0.38
    <bos>
    0.35
    Overnight
    0.34
     months
    0.34
    vernight
    0.32
    浸
    0.32
     days
    0.32
     WEEKS
    0.31
    Act Density 0.046%

    No Known Activations