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

    Neuronpedia

    INDEX
    Explanations

    dates written in a specific format with a comma after the day and year, followed by "REUTERS" and a high activation value for the forward slash ("/")

    oai_token-act-pair · gpt-3.5-turbo

    references to news agency citations or report formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.78
     worms
    -0.71
    worms
    -0.70
     prol
    -0.69
     beetles
    -0.68
     Rite
    -0.66
     idol
    -0.65
     stool
    -0.64
     queens
    -0.63
     craw
    -0.62
    POSITIVE LOGITS
    File
    0.92
    AFP
    0.88
    Flickr
    0.87
    Getty
    0.86
    Leon
    0.85
    David
    0.82
    Press
    0.81
    WAR
    0.80
    Scott
    0.80
    Brend
    0.79
    Act Density 0.022%

    No Known Activations