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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of “day number ordinal indicator month year”

    oai_token-act-pair · gpt-3.5-turbo

    references to specific quantities related to age groups or statistical data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ation
    -0.80
    omial
    -0.79
    lar
    -0.78
    ates
    -0.75
    itives
    -0.73
    fare
    -0.71
    hers
    -0.70
    ItemTracker
    -0.70
    atis
    -0.69
    ĸļ
    -0.68
    POSITIVE LOGITS
    fps
    0.91
    utical
    0.84
    nm
    0.83
    mph
    0.81
    %"
    0.70
     Seconds
    0.69
    ¯¯
    0.69
     seconds
    0.69
    etheus
    0.68
    th
    0.68
    Act Density 0.104%

    No Known Activations