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

    Neuronpedia

    INDEX
    Explanations

    actions or processes that involve creating, adding, showing, hiring, keeping, celebrating, installing, treating, hiding, running, making, putting, wrapping, closing, buying, or reporting

    oai_token-act-pair · gpt-3.5-turbo

    actions or processes involved in building, adding, or improving systems and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vent
    -0.70
     masters
    -0.67
    bomb
    -0.67
    ance
    -0.64
    rone
    -0.64
    empt
    -0.63
     unle
    -0.63
    stice
    -0.62
    eur
    -0.62
     gods
    -0.61
    POSITIVE LOGITS
    ometimes
    1.14
    omething
    1.14
    hift
    1.10
    pace
    1.10
    paces
    1.05
    ynthesis
    0.99
    uggest
    0.95
    afety
    0.90
    peed
    0.90
    everal
    0.87
    Act Density 0.290%

    No Known Activations