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

    Neuronpedia

    INDEX
    Explanations

    words related to reporting incidents or issues to authorities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "report" in various contexts related to documentation and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.73
    vous
    -0.69
    xtap
    -0.66
    enta
    -0.64
    wich
    -0.64
    osi
    -0.63
    east
    -0.63
     gauge
    -0.62
    atan
    -0.62
    wikipedia
    -0.62
    POSITIVE LOGITS
    ounces
    0.73
     sightings
    0.71
    Crash
    0.70
    Reporting
    0.68
    metry
    0.68
    ufact
    0.68
     reports
    0.65
     favorably
    0.64
    bugs
    0.64
    ribe
    0.64
    Act Density 0.056%

    No Known Activations