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

    Neuronpedia

    INDEX
    Explanations

    words related to organization, structure, and arrangement

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to order and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nadu
    -0.73
    peria
    -0.69
    ãĤ©
    -0.67
    attery
    -0.67
    SG
    -0.66
    ipedia
    -0.65
    rities
    -0.65
    vana
    -0.64
    reath
    -0.64
    aye
    -0.64
    POSITIVE LOGITS
    lies
    1.42
    liness
    1.23
    eous
    0.85
    etary
    0.84
    eering
    0.83
    ality
    0.79
    ifice
    0.76
    books
    0.75
    enance
    0.73
    book
    0.73
    Act Density 0.032%

    No Known Activations