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

    Neuronpedia

    INDEX
    Explanations

    phrases related to illegal activities, specifically involving finance

    oai_token-act-pair · gpt-3.5-turbo

    references to illicit activities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ding
    -0.71
    wcsstore
    -0.67
    é¾įå¥ij士
    -0.67
    lished
    -0.66
     compr
    -0.65
    è¦ļéĨĴ
    -0.64
    è¯
    -0.64
     palm
    -0.63
     Chomsky
    -0.63
    rano
    -0.62
    POSITIVE LOGITS
    inois
    1.52
    uminati
    1.47
    nesses
    1.13
    ustration
    1.10
    awar
    1.08
    usions
    1.04
    umin
    1.03
    Ill
    0.99
    icit
    0.99
    enium
    0.94
    Act Density 0.011%

    No Known Activations