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

    Neuronpedia

    INDEX
    Explanations

    references to morality, moral beliefs, and religious values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     biệt
    -0.52
    évaluateur
    -0.52
    RegressionTest
    -0.50
    ipedi
    -0.50
    DeleteCommand
    -0.50
    eira
    -0.50
     TREAT
    -0.47
    eip
    -0.45
     solstice
    -0.45
    TREAT
    -0.44
    POSITIVE LOGITS
     morals
    1.07
     moral
    0.89
     Moral
    0.86
     pious
    0.80
    moral
    0.79
    Moral
    0.79
     morality
    0.77
     morales
    0.75
     ethical
    0.73
    olesome
    0.73
    Act Density 0.369%

    No Known Activations