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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "Do"

    oai_token-act-pair · gpt-3.5-turbo

    questions posed to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.83
    )=(
    -0.70
    boarding
    -0.70
    workshop
    -0.69
    creen
    -0.67
    Software
    -0.65
    cream
    -0.64
     Azerb
    -0.63
     Handling
    -0.63
    EStreamFrame
    -0.62
    POSITIVE LOGITS
    omsday
    1.34
    ppel
    1.18
    herty
    1.12
    zens
    1.06
    lez
    1.05
    lyak
    0.98
    oley
    0.95
    ozy
    0.91
    ggies
    0.90
    oway
    0.90
    Act Density 0.081%

    No Known Activations