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

    Neuronpedia

    INDEX
    Explanations

    dates written in the format "Dec 9" or similar

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the date "December" in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.76
     awa
    -0.72
    lein
    -0.69
    ģ
    -0.67
    ooter
    -0.65
    stitial
    -0.65
    matical
    -0.65
     ambul
    -0.64
    john
    -0.63
    aho
    -0.63
    POSITIVE LOGITS
     Dec
    3.58
    Dec
    2.67
    dec
    2.19
     Nov
    2.18
     Oct
    2.10
     Feb
    2.05
     Aug
    2.05
     Jan
    1.97
     Sept
    1.76
     DEC
    1.75
    Act Density 0.008%

    No Known Activations