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

    Neuronpedia

    INDEX
    Explanations

    mentions of rulership, leadership, or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to governance and periods of leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     objects
    -0.64
    oros
    -0.64
     Ryder
    -0.64
    cest
    -0.60
     abstract
    -0.60
    gru
    -0.60
     bicycl
    -0.58
     Wass
    -0.58
     Rey
    -0.58
    ramer
    -0.57
    POSITIVE LOGITS
    manship
    0.81
     tenure
    0.81
    mates
    0.81
     lasted
    0.79
     abroad
    0.77
    mania
    0.74
     flourishing
    0.74
    quit
    0.71
     mate
    0.71
     spanning
    0.69
    Act Density 0.150%

    No Known Activations