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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governing or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to governing bodies or authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Vs
    -0.77
    Jet
    -0.77
    orne
    -0.77
    tein
    -0.76
    haar
    -0.76
    eele
    -0.74
    hma
    -0.74
    aro
    -0.74
     Kinnikuman
    -0.73
    jen
    -0.73
    POSITIVE LOGITS
     governing
    1.44
     governance
    0.88
     govern
    0.86
     conduc
    0.85
    verning
    0.79
     citiz
    0.79
     personalities
    0.78
    utical
    0.78
     governed
    0.78
     governs
    0.78
    Act Density 0.005%

    No Known Activations