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

    Neuronpedia

    INDEX
    Explanations

    concepts related to ethics and morality

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

    "Ethical" or "moral" concepts

    np_acts-logits-general · gemini-2.0-flash

    ethical and moral implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.69
    Tikang
    -0.57
    urtstag
    -0.55
    addPreferredGap
    -0.55
    Jegyzetek
    -0.55
    expandindo
    -0.54
     Stor
    -0.54
     Dom
    -0.53
    országban
    -0.53
    
    -0.52
    POSITIVE LOGITS
     ethics
    1.12
     moral
    1.10
     morals
    1.06
    ethics
    1.06
     Ethics
    1.04
    Ethics
    1.02
     Moral
    1.01
     morales
    1.00
     ethical
    0.99
    moral
    0.97
    Act Density 0.149%

    No Known Activations