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

    Neuronpedia

    INDEX
    Explanations

    mentions of high-ranking political figures, particularly Vice Presidents

    oai_token-act-pair · gpt-3.5-turbo

    references to various political figures and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plate
    -0.67
    NetMessage
    -0.65
     ende
    -0.65
     exting
    -0.65
     scrim
    -0.63
    phia
    -0.62
     panc
    -0.62
     contrace
    -0.61
    apest
    -0.59
    banks
    -0.59
    POSITIVE LOGITS
     Clancy
    0.75
    eur
    0.73
    iors
    0.72
     Marshal
    0.71
     Biden
    0.68
    ĺħ
    0.67
    vir
    0.67
     Lama
    0.66
    stown
    0.66
    rency
    0.64
    Act Density 0.034%

    No Known Activations