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

    Neuronpedia

    INDEX
    Explanations

    dates in the format Month Day-Year

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.68
     flyers
    -0.64
    £ı
    -0.61
     lining
    -0.61
     showc
    -0.60
     conscientious
    -0.60
     dime
    -0.59
     pestic
    -0.57
     hindsight
    -0.56
     planes
    -0.56
    POSITIVE LOGITS
     2010
    1.30
     2011
    1.29
     2009
    1.24
     2012
    1.21
     2007
    1.20
     2008
    1.20
     2006
    1.18
     2005
    1.13
     2013
    1.12
     2014
    1.11
    Act Density 0.022%

    No Known Activations