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

    Neuronpedia

    INDEX
    Explanations

    quantitative information related to government, politics, and finance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ij士
    -0.83
    NetMessage
    -0.81
    ¿½
    -0.77
    Kin
    -0.75
    catentry
    -0.73
     Scal
    -0.72
     Hallow
    -0.72
     Cros
    -0.71
     Pwr
    -0.70
    Pear
    -0.69
    POSITIVE LOGITS
    iment
    0.82
    ures
    0.81
    iciary
    0.75
     federation
    0.72
    enei
    0.71
    ét
    0.71
     authorization
    0.71
    orpor
    0.70
    orate
    0.70
    anic
    0.69
    Act Density 0.223%

    No Known Activations