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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental and political activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     chap
    -0.66
     Stores
    -0.64
     Hath
    -0.63
    azines
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
    izons
    -0.61
     flock
    -0.61
     Pixel
    -0.60
     pores
    -0.60
    haired
    -0.59
    POSITIVE LOGITS
     unacceptable
    1.03
     unfair
    0.98
     counterproductive
    0.98
     warranted
    0.98
     justified
    0.91
     "
    0.90
     legitimate
    0.89
     unethical
    0.88
     tant
    0.88
     unsustainable
    0.87
    Act Density 0.284%

    No Known Activations