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

    Neuronpedia

    INDEX
    Explanations

    mentions of different nationalities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    utherford
    -0.80
    odder
    -0.80
    anship
    -0.80
    track
    -0.76
    eus
    -0.75
    regor
    -0.75
    uably
    -0.74
    ully
    -0.73
    ording
    -0.73
    mble
    -0.73
    POSITIVE LOGITS
     nationals
    1.11
    apolis
    1.05
     Nadu
    1.01
     Embassy
    0.98
    istani
    0.97
    oslov
    0.95
     citizen
    0.94
     embassy
    0.92
     diplomats
    0.89
     soil
    0.89
    Act Density 0.773%

    No Known Activations