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

    Neuronpedia

    INDEX
    Explanations

    words related to government agencies and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to government agencies and security-related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weather
    -0.66
    given
    -0.64
    Äĩ
    -0.64
    bringer
    -0.64
    worthy
    -0.62
    bring
    -0.59
     subscribed
    -0.59
    wordpress
    -0.59
    hower
    -0.59
    stellar
    -0.58
    POSITIVE LOGITS
     Regulatory
    0.94
     Compensation
    0.88
     Agency
    0.86
     Association
    0.83
     Improvement
    0.81
     Administration
    0.81
     Franch
    0.81
     Perspect
    0.81
     Simulator
    0.80
     Unit
    0.80
    Act Density 0.177%

    No Known Activations