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

    Neuronpedia

    INDEX
    Explanations

    dates in specific month and year formats

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     wasteland
    -0.64
     ado
    -0.61
    ioned
    -0.60
    othe
    -0.58
     plat
    -0.57
    eton
    -0.55
    rn
    -0.54
     ageing
    -0.54
     curls
    -0.53
    ersed
    -0.53
    POSITIVE LOGITS
     2017
    1.38
     2015
    1.33
     2016
    1.33
     2014
    1.30
     2018
    1.28
     2013
    1.24
     2012
    1.19
     2011
    1.16
     2010
    1.13
     2001
    1.12
    Act Density 0.097%

    No Known Activations