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

    Neuronpedia

    INDEX
    Explanations

    news articles or reports citing sources such as newspapers

    oai_token-act-pair · gpt-3.5-turbo

    citations and reports from various news sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toast
    -0.79
    odynamic
    -0.76
    ield
    -0.76
    pired
    -0.75
    anging
    -0.72
     brood
    -0.72
     grandchildren
    -0.70
    adow
    -0.68
     clay
    -0.67
    vati
    -0.67
    POSITIVE LOGITS
     Inquis
    0.86
     Investigative
    0.83
     Sources
    0.81
     citing
    0.78
     Fast
    0.77
     Insider
    0.77
     quoting
    0.76
    BBC
    0.75
     Fact
    0.75
    Sources
    0.75
    Act Density 0.266%

    No Known Activations