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

    Neuronpedia

    INDEX
    Explanations

    terms related to ethical considerations and approvals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ethical reasons, considerations, implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arrar
    -0.56
     Ino
    -0.56
    orna
    -0.54
    lola
    -0.53
    Bain
    -0.52
    nin
    -0.52
    bua
    -0.52
    .)}
    -0.51
    oban
    -0.51
    lasses
    -0.50
    POSITIVE LOGITS
     ethical
    1.94
     Ethical
    1.84
    Ethical
    1.84
    ethical
    1.77
     ethics
    1.62
     ethically
    1.56
     Ethics
    1.55
    Ethics
    1.48
     ética
    1.42
    ethics
    1.34
    Act Density 0.011%

    No Known Activations