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

    Neuronpedia

    INDEX
    Explanations

    terms related to various societal issues, such as health conditions, discrimination, and social disparities

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social issues and health concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orsche
    -0.68
     Dmit
    -0.62
     Chevy
    -0.62
     Airbus
    -0.61
     Jeep
    -0.59
     Dictionary
    -0.59
    IUM
    -0.58
     Porsche
    -0.58
     Cadillac
    -0.57
    ãĥ³ãĤ¸
    -0.56
    POSITIVE LOGITS
     illegally
    0.80
    their
    0.79
     apiece
    0.77
     backgrounds
    0.71
     compared
    0.71
    agar
    0.70
     themselves
    0.70
    secondary
    0.68
     voluntarily
    0.67
    gat
    0.66
    Act Density 0.647%

    No Known Activations