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

    Neuronpedia

    INDEX
    Explanations

    words related to specific technical terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to various forms of health, safety, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemThumbnailImage
    -0.63
     mathemat
    -0.62
    ADRA
    -0.62
    Thumbnail
    -0.62
    xual
    -0.61
    veyard
    -0.60
     reckoning
    -0.60
    staking
    -0.58
     teased
    -0.57
    Ö¼
    -0.54
    POSITIVE LOGITS
    pes
    0.69
    acts
    0.65
     pieces
    0.63
    ieties
    0.62
     Messages
    0.60
    facts
    0.60
    anes
    0.59
    isively
    0.59
     messages
    0.59
    coins
    0.58
    Act Density 0.761%

    No Known Activations