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

    Neuronpedia

    INDEX
    Explanations

    topics related to specific objects or concepts, such as dogs, guns, horses, cars, drugs, drones, trees, arrays, superheroes, robots, vampires, zombies, and eggs

    oai_token-act-pair · gpt-3.5-turbo

    references to various risks and recreational items related to violence and danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļé
    -0.62
     Candidate
    -0.62
     submission
    -0.61
     Submission
    -0.60
    Attempts
    -0.60
    ilogy
    -0.60
    MENTS
    -0.59
     VID
    -0.59
     claimant
    -0.58
     subsequ
    -0.58
    POSITIVE LOGITS
    paces
    1.28
    cale
    1.17
    pace
    1.16
    hip
    1.12
    creen
    1.11
    poons
    1.11
    ynthesis
    1.09
    hips
    1.09
    peed
    1.09
    mith
    1.09
    Act Density 0.421%

    No Known Activations