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

    Neuronpedia

    INDEX
    Explanations

    sources or reports of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate sources or authorship in reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stakes
    -0.71
    wcsstore
    -0.71
     largeDownload
    -0.71
    hene
    -0.68
    cest
    -0.68
     embodies
    -0.67
     cubic
    -0.66
    oves
    -0.66
     grips
    -0.66
    anuts
    -0.65
    POSITIVE LOGITS
     Ellen
    0.87
     Tina
    0.85
     Seymour
    0.83
     Trey
    0.83
     Gerald
    0.82
     Christine
    0.82
     Jonathan
    0.81
     Evan
    0.80
     Jeffrey
    0.79
     reporters
    0.78
    Act Density 0.157%

    No Known Activations