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

    Neuronpedia

    INDEX
    Explanations

    political and philosophical ideologies and principles

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to values and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soon
    -0.87
    gren
    -0.73
    rm
    -0.73
    ̶
    -0.71
    ptoms
    -0.71
    fold
    -0.70
    BE
    -0.69
    NetMessage
    -0.69
     è£ıè¦ļéĨĴ
    -0.69
     Ples
    -0.68
    POSITIVE LOGITS
     egalitarian
    1.36
     individuality
    1.33
     liberty
    1.32
     equality
    1.30
     patriotism
    1.30
     humility
    1.30
     purity
    1.28
     volunt
    1.27
     fairness
    1.26
     tolerance
    1.26
    Act Density 0.288%

    No Known Activations