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

    Neuronpedia

    INDEX
    Explanations

    references to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to news sources and their reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.80
    venge
    -0.74
    ĪĴ
    -0.72
     toast
    -0.71
    tsy
    -0.69
     cort
    -0.68
     clay
    -0.67
    anging
    -0.66
    ield
    -0.66
    respective
    -0.65
    POSITIVE LOGITS
     Sources
    0.84
     quoting
    0.83
     citing
    0.82
     sources
    0.80
     Investigative
    0.78
     unnamed
    0.77
     excerpts
    0.76
     quotes
    0.74
     Editorial
    0.73
     Inquis
    0.72
    Act Density 0.273%

    No Known Activations