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

    Neuronpedia

    INDEX
    Explanations

    the word "Capitol"

    oai_token-act-pair · gpt-4-turbo

    references to a specific location, specifically "Capitol."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Capitol building or related political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gger
    -0.81
    ãģ¦
    -0.75
     Bucc
    -0.72
    hari
    -0.71
    earch
    -0.70
    err
    -0.68
    words
    -0.66
    facts
    -0.65
    Episode
    -0.65
    %%%%
    -0.65
    POSITIVE LOGITS
    itol
    1.19
     Capitol
    1.03
     Hill
    0.94
    rament
    0.83
     dome
    0.79
     lobbying
    0.73
     entrances
    0.73
    ratulations
    0.72
     sten
    0.71
     Heights
    0.71
    Act Density 0.015%

    No Known Activations