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

    Neuronpedia

    INDEX
    Explanations

    words related to law, politics, and government

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    ãĥĵ
    -0.66
     mats
    -0.65
     hobby
    -0.65
     codes
    -0.63
     beginners
    -0.63
     pract
    -0.62
     licence
    -0.62
    units
    -0.62
     util
    -0.62
    POSITIVE LOGITS
     Gingrich
    0.98
    ghazi
    0.97
    Moreover
    0.96
     Krugman
    0.94
     Pelosi
    0.93
    Indeed
    0.92
    Meanwhile
    0.92
    Republicans
    0.92
     Fiorina
    0.90
     Rosenstein
    0.89
    Act Density 0.578%

    No Known Activations