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

    Neuronpedia

    INDEX
    Explanations

    references to government bodies, specifically the term "Congress"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     increa
    -0.88
     encomp
    -0.85
     intersper
    -0.82
     shenan
    -0.82
     guarante
    -0.81
     affor
    -0.80
     hairc
    -0.78
     fuf
    -0.78
     effe
    -0.75
     scrat
    -0.75
    POSITIVE LOGITS
     Congress
    1.37
    Congress
    1.24
     congress
    1.08
     congressional
    0.97
    congress
    0.93
     Congressional
    0.92
     CONGRESS
    0.90
     Congrès
    0.77
    ressional
    0.76
     congressman
    0.74
    Act Density 0.067%

    No Known Activations