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

    Neuronpedia

    INDEX
    Explanations

    sentences that emphasize importance or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts associated with personal responsibility and collective implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cms
    -0.72
    osterone
    -0.71
    etheus
    -0.64
    \/
    -0.64
     cricket
    -0.62
    acan
    -0.60
     Leviathan
    -0.59
     Lah
    -0.58
     Cheong
    -0.57
    iage
    -0.57
    POSITIVE LOGITS
    qualified
    0.72
     unus
    0.69
     goodbye
    0.67
     unprotected
    0.67
    ezvous
    0.66
    tu
    0.65
    bye
    0.64
     inher
    0.59
     toast
    0.58
    vana
    0.57
    Act Density 0.206%

    No Known Activations