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

    Neuronpedia

    INDEX
    Explanations

    phrases related to moral values and principles

    oai_token-act-pair · gpt-3.5-turbo

    references to core values and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geon
    -0.76
    女
    -0.73
    --------------------------------------------------------
    -0.72
    waves
    -0.69
    fac
    -0.68
    sie
    -0.67
    \/\/
    -0.64
    OVA
    -0.63
    Sus
    -0.63
    brain
    -0.62
    POSITIVE LOGITS
     values
    0.82
     ideals
    0.79
     Values
    0.76
     beliefs
    0.75
    values
    0.75
     propositions
    0.74
     proposition
    0.74
     principles
    0.73
     embodied
    0.72
     sensibilities
    0.71
    Act Density 0.016%

    No Known Activations