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

    Neuronpedia

    INDEX
    Explanations

    phrases related to fundamental principles or doctrines

    oai_token-act-pair · gpt-3.5-turbo

    references to fundamental principles and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minster
    -0.82
    quer
    -0.68
    ummer
    -0.67
    ilation
    -0.66
    essions
    -0.66
    otte
    -0.65
    hner
    -0.65
    ammers
    -0.65
    NetMessage
    -0.62
    azo
    -0.62
    POSITIVE LOGITS
     principles
    1.02
    ciples
    0.96
     principle
    0.92
     underpin
    0.90
    cipled
    0.87
     guiding
    0.85
     underlying
    0.83
     Principles
    0.78
     precept
    0.77
    ually
    0.77
    Act Density 0.032%

    No Known Activations