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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    numeric age references in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.73
    irie
    -0.70
    uras
    -0.69
    imaru
    -0.68
     Balk
    -0.68
    earch
    -0.67
     toile
    -0.67
    ihu
    -0.67
    ido
    -0.65
    itive
    -0.64
    POSITIVE LOGITS
    ottest
    0.75
    utch
    0.74
    bourg
    0.73
    254
    0.72
    368
    0.71
    degree
    0.70
    678
    0.70
    658
    0.69
    655
    0.68
    65
    0.68
    Act Density 0.272%

    No Known Activations