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

    Neuronpedia

    INDEX
    Explanations

    references to concepts related to morality and ethics

    oai_token-act-pair · gpt-3.5-turbo

    concepts and discussions surrounding morality and ethical principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eding
    -0.81
    WER
    -0.79
    berry
    -0.72
    ept
    -0.72
    eds
    -0.72
    eworld
    -0.71
    upon
    -0.71
    location
    -0.70
    aways
    -0.68
    eded
    -0.66
    POSITIVE LOGITS
     contag
    0.91
    ocracy
    0.83
     guiActiveUn
    0.78
     morality
    0.75
    onomic
    0.74
    anship
    0.73
     Petr
    0.70
     srfAttach
    0.69
     ethics
    0.69
    onom
    0.68
    Act Density 0.009%

    No Known Activations