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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fingerprints
    -0.68
     carefully
    -0.64
     deliberately
    -0.63
     exagger
    -0.63
     unusually
    -0.63
     quietly
    -0.62
     surprised
    -0.60
     intentionally
    -0.60
     nonetheless
    -0.60
     knowingly
    -0.59
    POSITIVE LOGITS
    iverse
    0.93
    osphere
    0.92
    isphere
    0.85
    iterranean
    0.85
    abase
    0.81
    orld
    0.80
    assic
    0.80
    liga
    0.79
    cosystem
    0.78
     universe
    0.74
    Act Density 0.831%

    No Known Activations