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

    Neuronpedia

    INDEX
    Explanations

    social or political commentary and criticism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rn
    -0.65
    ayette
    -0.65
    plain
    -0.63
    hur
    -0.61
    ASC
    -0.61
    irlf
    -0.61
    aith
    -0.61
     eminent
    -0.59
    planes
    -0.58
    cham
    -0.58
    POSITIVE LOGITS
     2016
    1.14
     2015
    1.11
     2017
    1.10
     2014
    1.09
     2018
    1.06
     2010
    1.03
     2012
    1.02
     2013
    1.00
     2008
    0.93
     2011
    0.93
    Act Density 0.024%

    No Known Activations