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

    Neuronpedia

    INDEX
    Explanations

    dates in the format month followed by day

    oai_token-act-pair · gpt-3.5-turbo

    specific mentions of dates or months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.70
     cumbers
    -0.68
     basket
    -0.68
     multiplying
    -0.63
    ngth
    -0.61
    ylum
    -0.61
     Flavoring
    -0.59
     unaff
    -0.58
     tsun
    -0.58
    é¾įå¥ij士
    -0.58
    POSITIVE LOGITS
     04
    0.84
     07
    0.83
     29
    0.81
     31
    0.80
     08
    0.79
     27
    0.79
     03
    0.79
     01
    0.78
     06
    0.78
     28
    0.78
    Act Density 0.045%

    No Known Activations