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

    Neuronpedia

    INDEX
    Explanations

    names of political figures with varying levels of importance

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and their associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mortal
    -0.72
     Variety
    -0.70
    Origin
    -0.70
     Cary
    -0.67
    Researchers
    -0.66
    Scient
    -0.66
    FOX
    -0.66
    Native
    -0.65
    rawdownloadcloneembedreportprint
    -0.65
     Researchers
    -0.64
    POSITIVE LOGITS
     appoint
    1.00
     administration
    0.94
     Jinping
    0.94
    isma
    0.88
     reelection
    0.87
     appointed
    0.86
     elected
    0.85
     administ
    0.85
    jriwal
    0.82
    enei
    0.82
    Act Density 0.174%

    No Known Activations