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

    Neuronpedia

    INDEX
    Explanations

    references to pictures or images

    oai_token-act-pair · gpt-3.5-turbo

    references to images, photos, and rankings in a context indicating high importance or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Friend
    -0.69
    ounded
    -0.62
    PsyNetMessage
    -0.61
    weak
    -0.59
    oult
    -0.58
    ãĥ£
    -0.58
    timeout
    -0.58
    ryu
    -0.58
    Madison
    -0.58
    urgy
    -0.57
    POSITIVE LOGITS
     contender
    0.70
     earners
    0.68
    nings
    0.65
    entin
    0.63
    roller
    0.62
    ranking
    0.61
    holder
    0.61
    acher
    0.61
    illet
    0.58
     teaser
    0.58
    Act Density 0.143%

    No Known Activations