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

    Neuronpedia

    INDEX
    Explanations

    country names

    oai_token-act-pair · gpt-3.5-turbo

    references to nationalities and their governments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byss
    -0.83
    arth
    -0.83
    ////
    -0.78
    maxwell
    -0.78
    INESS
    -0.77
    mble
    -0.75
    LESS
    -0.75
    raviolet
    -0.74
    aunder
    -0.73
    lished
    -0.72
    POSITIVE LOGITS
     delegation
    1.03
     government
    0.98
     nationalist
    0.93
     nationals
    0.93
     Government
    0.92
     Communist
    0.91
     embassy
    0.91
     consulate
    0.90
     State
    0.88
     nationalists
    0.86
    Act Density 0.120%

    No Known Activations