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

    Neuronpedia

    INDEX
    Explanations

    dates with news agency names

    oai_token-act-pair · gpt-3.5-turbo

    markers of citations or references to news agency content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frozen
    -0.68
     Stout
    -0.67
     Exhibition
    -0.67
     Clo
    -0.64
     Penny
    -0.62
     Downs
    -0.61
     Deg
    -0.61
     Dock
    -0.61
     Squadron
    -0.60
     Stall
    -0.60
    POSITIVE LOGITS
    WASHINGTON
    0.93
    NA
    0.86
    ccording
    0.82
    BBC
    0.80
    externalActionCode
    0.80
    POL
    0.77
    Reuters
    0.76
    Aust
    0.76
    rawdownloadcloneembedreportprint
    0.76
    IAL
    0.75
    Act Density 0.129%

    No Known Activations