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

    Neuronpedia

    INDEX
    Explanations

    periods represented by dashes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     gum
    -0.77
     Dickinson
    -0.74
     Quan
    -0.72
     cov
    -0.70
     discrim
    -0.69
     proport
    -0.67
     antiv
    -0.66
     Coin
    -0.65
     negotiator
    -0.65
     Deity
    -0.65
    POSITIVE LOGITS
    2010
    1.27
    2011
    1.25
    2006
    1.25
    2009
    1.25
    2007
    1.21
    2004
    1.20
    2005
    1.20
    2008
    1.20
    1945
    1.20
    2012
    1.20
    Act Density 0.032%

    No Known Activations