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

    Neuronpedia

    INDEX
    Explanations

    texts related to guiding principles or values

    oai_token-act-pair · gpt-3.5-turbo

    references to guiding principles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sg
    -0.85
    âĹ¼
    -0.74
    taboola
    -0.70
    eb
    -0.69
    bor
    -0.69
    gg
    -0.67
    ctic
    -0.67
    olla
    -0.67
    cknowled
    -0.64
     Purchase
    -0.64
    POSITIVE LOGITS
     principles
    1.30
     Principles
    0.99
    ciples
    0.95
     principle
    0.95
     principals
    0.89
     prin
    0.82
     underlying
    0.81
     fundamentals
    0.80
     guiding
    0.79
    cipled
    0.78
    Act Density 0.006%

    No Known Activations