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

    Neuronpedia

    INDEX
    Explanations

    words related to moral concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to morality and virtue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eding
    -0.85
    location
    -0.81
    WER
    -0.78
    gow
    -0.75
    funding
    -0.75
    mining
    -0.72
    CAST
    -0.72
    raltar
    -0.71
    sites
    -0.69
    overed
    -0.69
    POSITIVE LOGITS
     righteousness
    0.85
     precept
    0.84
    ocracy
    0.81
     incarn
    0.81
    ocratic
    0.80
     deeds
    0.78
     indignation
    0.76
     compass
    0.71
     morally
    0.68
     virtuous
    0.68
    Act Density 0.053%

    No Known Activations