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

    Neuronpedia

    INDEX
    Explanations

    references to ethical or moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     certification
    -0.47
    鑑
    -0.45
    Page
    -0.45
    ntax
    -0.44
    凝
    -0.43
     Given
    -0.42
     Del
    -0.42
    Given
    -0.42
    </h5>
    -0.42
    кон
    -0.42
    POSITIVE LOGITS
     <=",
    0.90
     تانيه
    0.85
    featureID
    0.84
    :✨
    0.82
    +#+#
    0.81
    bootstrapcdn
    0.78
     незавершена
    0.77
     propOrder
    0.76
    onAttach
    0.76
    脚注の使い方
    0.75
    Act Density 0.425%

    No Known Activations