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

    Neuronpedia

    INDEX
    Explanations

    dates, specifically the word "Twenty" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Twenty" followed by numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Syndicate
    -0.66
    chio
    -0.64
    displayText
    -0.63
     kicker
    -0.59
    henko
    -0.58
     Painter
    -0.58
     Loans
    -0.58
    Activity
    -0.58
     formation
    -0.57
    agate
    -0.57
    POSITIVE LOGITS
    ishers
    1.03
    eteen
    1.02
    isher
    0.97
    een
    0.92
     Thousand
    0.92
    Eight
    0.91
     thousand
    0.90
    eenth
    0.90
    irteen
    0.89
    teen
    0.86
    Act Density 0.007%

    No Known Activations