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

    Neuronpedia

    INDEX
    Explanations

    government or official agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to various agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sticks
    -0.82
    erous
    -0.79
    meyer
    -0.73
    stad
    -0.72
    jiang
    -0.71
    lasses
    -0.69
     Skywalker
    -0.67
    ening
    -0.67
    bring
    -0.66
    dden
    -0.66
    POSITIVE LOGITS
     Agency
    0.93
    ENCY
    0.85
    ption
    0.83
    UTH
    0.82
    BILITIES
    0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.73
     Coord
    0.72
     Employees
    0.72
     Administrator
    0.70
    encies
    0.70
    Act Density 0.020%

    No Known Activations