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

    Neuronpedia

    INDEX
    Explanations

    dates formatted as day-month-year

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical dates in the text, particularly the day of the month

    oai_token-act-pair · gpt-4-turbo

    dates and specific numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imated
    -0.78
    igham
    -0.71
    edIn
    -0.69
    withstanding
    -0.69
    atown
    -0.68
    imeters
    -0.65
    imeter
    -0.64
    isphere
    -0.64
    rew
    -0.63
     scissors
    -0.62
    POSITIVE LOGITS
    th
    0.80
     Sands
    0.74
    678
    0.74
    ESE
    0.72
    NESS
    0.70
    677
    0.69
    %"
    0.68
    %]
    0.67
    EVA
    0.67
    ths
    0.67
    Act Density 0.333%

    No Known Activations