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

    Neuronpedia

    INDEX
    Explanations

    statistics and trends over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time references or changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfocusedRange
    -0.86
    oeuv
    -0.71
    dimensional
    -0.70
    bart
    -0.69
    REDACTED
    -0.69
    orah
    -0.68
    Ĥª
    -0.67
    oreal
    -0.67
    ãĤĮ
    -0.66
    dream
    -0.66
    POSITIVE LOGITS
     2010
    0.98
     inception
    0.98
     enactment
    0.98
     2009
    0.95
     2008
    0.95
     passage
    0.94
     recession
    0.92
     2007
    0.91
     2005
    0.90
     2011
    0.90
    Act Density 0.198%

    No Known Activations