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

    Neuronpedia

    INDEX
    Explanations

    updated information in news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Updated"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.91
    ften
    -0.77
    marks
    -0.77
    bour
    -0.76
    acht
    -0.75
    OPA
    -0.74
    belt
    -0.73
    marked
    -0.73
    holes
    -0.73
    thing
    -0.72
    POSITIVE LOGITS
     Updates
    0.83
    Updated
    0.80
     Update
    0.75
    Attempts
    0.75
     timestamp
    0.74
    Posted
    0.74
     Comments
    0.73
    Published
    0.72
     Dates
    0.72
     EDIT
    0.72
    Act Density 0.008%

    No Known Activations