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

    Neuronpedia

    INDEX
    Explanations

    legal terms and mentions of legal regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hin
    -0.74
    uilding
    -0.71
    eton
    -0.70
    osaurus
    -0.69
    pring
    -0.68
    nesday
    -0.67
    idates
    -0.67
    ourney
    -0.65
    roup
    -0.64
     yourselves
    -0.64
    POSITIVE LOGITS
     laws
    1.29
     rules
    1.27
     requirements
    1.23
     guidelines
    1.21
     statutes
    1.21
     norms
    1.21
     principles
    1.18
     prohibitions
    1.18
     regulations
    1.16
     tenets
    1.15
    Act Density 0.341%

    No Known Activations