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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to positions of political power or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to political power dynamics and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Consumer
    -0.75
     bucket
    -0.71
    Lear
    -0.68
     Lent
    -0.68
    Parent
    -0.66
    Uncommon
    -0.66
     detector
    -0.66
     bandwidth
    -0.64
     buckets
    -0.64
    Native
    -0.61
    POSITIVE LOGITS
     overth
    0.92
     ousted
    0.91
    unta
    0.88
     presided
    0.86
    itol
    0.85
     Tripoli
    0.84
     elections
    0.84
     democratically
    0.81
    lords
    0.80
    govern
    0.79
    Act Density 0.289%

    No Known Activations