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

    Neuronpedia

    INDEX
    Explanations

    references to news reports or coverage

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "report" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.83
    ophers
    -0.73
    antics
    -0.73
    uit
    -0.70
    conservancy
    -0.69
    etsk
    -0.68
    rongh
    -0.67
    uits
    -0.66
     palate
    -0.65
    ophone
    -0.64
    POSITIVE LOGITS
    è¦ļéĨĴ
    0.89
     quoting
    0.84
     reports
    0.83
    age
    0.83
     sources
    0.80
     quotes
    0.80
    WASHINGTON
    0.77
     rumors
    0.76
     leaked
    0.76
     quoted
    0.75
    Act Density 0.055%

    No Known Activations