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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "vacuum"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of “vacuum.”

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hig
    -0.81
    ynasty
    -0.79
    uscript
    -0.76
    igel
    -0.76
    ihad
    -0.75
    kt
    -0.72
    itia
    -0.72
    eworld
    -0.71
    esty
    -0.70
    doms
    -0.70
    POSITIVE LOGITS
     cleaners
    1.18
     cleaner
    1.08
     vacuum
    0.92
     chamber
    0.81
     tube
    0.77
     tubes
    0.76
     chambers
    0.76
     perme
    0.76
     aspiration
    0.76
     oven
    0.72
    Act Density 0.019%

    No Known Activations