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

    Neuronpedia

    INDEX
    Explanations

    references to responsible AI development and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentView
    -0.18
    mez
    -0.17
    stal
    -0.16
    üstü
    -0.15
    omen
    -0.14
    ÛĮزÛĮ
    -0.14
    oku
    -0.14
    contr
    -0.14
    elo
    -0.13
    ÏĢει
    -0.13
    POSITIVE LOGITS
     ethical
    0.33
     ethics
    0.29
     Ethics
    0.29
     Eth
    0.27
     eth
    0.27
    ethical
    0.26
    Eth
    0.24
     privacy
    0.23
     ethic
    0.22
     moral
    0.20
    Act Density 0.147%

    No Known Activations