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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    dates, specifically those in November

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    king
    -0.83
    ldon
    -0.81
    gotten
    -0.76
    jriwal
    -0.76
    pires
    -0.76
    cher
    -0.74
    urdy
    -0.71
    ught
    -0.71
    utenberg
    -0.71
    ked
    -0.71
    POSITIVE LOGITS
     2012
    0.85
     2014
    0.85
     2015
    0.82
     2016
    0.81
     2013
    0.80
    е
    0.80
     1942
    0.77
     1941
    0.77
     2010
    0.76
     2011
    0.76
    Act Density 0.022%

    No Known Activations