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

    Neuronpedia

    INDEX
    Explanations

    slashes followed by dates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     divest
    -0.73
     brim
    -0.69
     proceeds
    -0.69
     concede
    -0.67
     closer
    -0.66
     venture
    -0.65
     conceive
    -0.65
     roam
    -0.63
     eaves
    -0.63
     boast
    -0.62
    POSITIVE LOGITS
    2018
    1.52
    2017
    1.51
    2015
    1.49
    2014
    1.46
    2013
    1.44
    2016
    1.44
    2012
    1.43
    2011
    1.34
    2008
    1.30
    2006
    1.30
    Act Density 0.025%

    No Known Activations