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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "how" or "what" such as "howling" or "what if"

    oai_token-act-pair · gpt-3.5-turbo

    questions and inquiries related to actions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mechdragon
    -0.66
     autonomous
    -0.61
     refining
    -0.60
     infiltr
    -0.59
     silenced
    -0.59
     qualified
    -0.58
     compens
    -0.58
     shedding
    -0.58
     wise
    -0.57
     compensated
    -0.57
    POSITIVE LOGITS
    soever
    1.37
    pper
    1.11
    itz
    1.10
    itzer
    1.08
    ppers
    1.06
    ells
    0.98
    abouts
    0.96
    sth
    0.95
    leys
    0.95
    lers
    0.95
    Act Density 0.093%

    No Known Activations