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

    Neuronpedia

    INDEX
    Explanations

    dates and months

    oai_token-act-pair · gpt-3.5-turbo

    dates and months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DonaldTrump
    -1.13
    ðŁ
    -1.00
    Trump
    -0.95
     âĢķ
    -0.89
    eneg
    -0.84
     ðŁ
    -0.82
    âĺ
    -0.80
    trump
    -0.80
     ko
    -0.79
    Donald
    -0.78
    POSITIVE LOGITS
     2010
    2.16
     2011
    2.11
     2009
    2.06
     2008
    1.90
     2012
    1.87
    2010
    1.78
     2007
    1.75
    2011
    1.74
    2009
    1.66
     2006
    1.65
    Act Density 0.206%

    No Known Activations