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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases related to technical specifications or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with data storage and retrieval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERSON
    -0.68
    igl
    -0.67
    apa
    -0.66
    Engineers
    -0.66
    ONY
    -0.64
    nw
    -0.64
     Harvey
    -0.62
    Alert
    -0.59
    negie
    -0.58
    Icon
    -0.58
    POSITIVE LOGITS
    hood
    0.65
    foundland
    0.64
    izers
    0.58
    etheless
    0.58
    noxious
    0.57
     derog
    0.56
    worthiness
    0.56
    isin
    0.55
    liness
    0.55
    mentioned
    0.55
    Act Density 0.699%

    No Known Activations