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

    Neuronpedia

    INDEX
    Explanations

    government departments and agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to government departments and agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conversions
    -0.77
     domestically
    -0.73
     worldwide
    -0.70
     geop
    -0.69
     embodiments
    -0.68
     biases
    -0.67
     newcomers
    -0.66
     momentum
    -0.66
     notch
    -0.65
     chants
    -0.65
    POSITIVE LOGITS
    abulary
    1.02
    bernatorial
    0.97
     Registry
    0.93
    istrates
    0.92
     District
    0.91
     Association
    0.90
     Exchange
    0.88
     Examination
    0.88
     Lic
    0.86
     Legislature
    0.86
    Act Density 0.156%

    No Known Activations