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

    Neuronpedia

    INDEX
    Explanations

    multi-digit numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly years and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aye
    -0.78
    aeus
    -0.77
    eton
    -0.75
    achu
    -0.73
    reek
    -0.71
    andise
    -0.71
    eners
    -0.71
    akes
    -0.71
    eday
    -0.69
    reen
    -0.68
    POSITIVE LOGITS
    20439
    1.01
    384
    0.86
    6666
    0.79
    0100
    0.77
    554
    0.74
    557
    0.71
    MHz
    0.71
    752
    0.70
    ïve
    0.69
     DEBUG
    0.69
    Act Density 0.084%

    No Known Activations