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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ethical and moral considerations

    oai_token-act-pair · gpt-3.5-turbo

    references to ethical and moral issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jong
    -0.84
    hof
    -0.83
    acular
    -0.81
    down
    -0.79
    gow
    -0.75
    peak
    -0.75
    xual
    -0.74
    upt
    -0.74
    ings
    -0.71
    aunts
    -0.71
    POSITIVE LOGITS
    onomic
    1.02
     dile
    0.99
    ethical
    0.98
     ethical
    0.87
     conscience
    0.79
     hazard
    0.79
     ethics
    0.78
     qual
    0.76
     violations
    0.76
     disclosure
    0.75
    Act Density 0.016%

    No Known Activations