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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative behaviors and consequences, such as drug abuse and failure

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.81
    etheless
    -0.67
    EMBER
    -0.64
    EMP
    -0.62
     )]
    -0.62
    enter
    -0.61
    zik
    -0.61
    ]]
    -0.61
    Recommend
    -0.60
     largeDownload
    -0.60
    POSITIVE LOGITS
     notwithstanding
    0.85
     etc
    0.80
     everywhere
    0.74
    !),
    0.72
     gal
    0.71
     abound
    0.70
    !,
    0.68
     or
    0.67
     buzzing
    0.65
     mattered
    0.65
    Act Density 1.238%

    No Known Activations