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

    Neuronpedia

    INDEX
    Explanations

    discussions concerning moral and ethical beliefs and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StackNavigator
    -0.52
    PDATE
    -0.49
    UrlResolution
    -0.45
    findpost
    -0.43
    locene
    -0.43
    jaci
    -0.42
    +#+#
    -0.41
     hâte
    -0.41
     disparu
    -0.41
    <_>
    -0.40
    POSITIVE LOGITS
     moral
    2.27
     ethical
    2.22
     ethics
    2.14
     morality
    1.95
    moral
    1.89
     Ethical
    1.88
     Moral
    1.88
     morals
    1.88
     Ethics
    1.84
     morally
    1.84
    Act Density 0.594%

    No Known Activations