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

    Neuronpedia

    INDEX
    Explanations

    dates in the month/day format

    oai_token-act-pair · gpt-3.5-turbo

    specific dates within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.64
    ortunately
    -0.62
     pione
    -0.62
     conflic
    -0.62
     unnecess
    -0.61
    ThumbnailImage
    -0.61
     newcom
    -0.61
    Þ
    -0.61
     practition
    -0.61
     glim
    -0.60
    POSITIVE LOGITS
     29
    1.04
     27
    1.00
     26
    0.99
     23
    0.98
     28
    0.98
     31
    0.98
     19
    0.97
     22
    0.97
     21
    0.97
     24
    0.95
    Act Density 0.133%

    No Known Activations