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

    Neuronpedia

    INDEX
    Explanations

    keywords related to political and social issues, such as government actions, legal challenges, and public sector decisions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hement
    -1.39
    uly
    -1.17
    acan
    -1.17
    anus
    -1.16
    ustom
    -1.07
    oons
    -1.02
    apan
    -1.01
    ako
    -1.01
    pard
    -1.00
    geons
    -1.00
    POSITIVE LOGITS
    JUST
    1.12
     marrow
    0.99
    ãĤ´ãĥ³
    0.98
    ³³³³³³³³³³³³³³³³
    0.96
    ccording
    0.95
     policing
    0.90
    ++++++++++++++++
    0.90
    ³³³³³³³³
    0.87
     Carbuncle
    0.87
    ======
    0.85
    Act Density 2.044%

    No Known Activations