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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing reported information

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "According to" indicating sources or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.86
    apons
    -0.83
    blast
    -0.75
    76561
    -0.71
    aden
    -0.68
    obyl
    -0.67
     ashore
    -0.67
    ãĥĵ
    -0.67
    20439
    -0.66
    eg
    -0.65
    POSITIVE LOGITS
    Ĥİ
    0.80
    Format
    0.74
     sources
    0.73
     Sources
    0.72
    Rank
    0.72
    chwitz
    0.71
    Ŀ
    0.71
    Ł
    0.70
    edly
    0.68
    encies
    0.67
    Act Density 0.042%

    No Known Activations