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

    Neuronpedia

    INDEX
    Explanations

    names of European political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly politicians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ictionary
    -0.84
    awar
    -0.84
    conservancy
    -0.79
    abies
    -0.77
    orage
    -0.77
    othal
    -0.77
    iqueness
    -0.76
    aho
    -0.76
    udder
    -0.75
    acea
    -0.75
    POSITIVE LOGITS
     Hollande
    1.18
     Macron
    1.14
     François
    1.02
     Francois
    1.00
     Mou
    0.95
     Fou
    0.91
     Renault
    0.90
     Michel
    0.89
     Gou
    0.85
     Santos
    0.84
    Act Density 0.035%

    No Known Activations