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

    Neuronpedia

    INDEX
    Explanations

    terms related to democracy

    oai_token-act-pair · gpt-3.5-turbo

    references to democracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.76
    ergy
    -0.74
    abee
    -0.71
    iple
    -0.70
    Contact
    -0.70
    FU
    -0.69
    senal
    -0.69
    details
    -0.69
    hews
    -0.68
    ulla
    -0.67
    POSITIVE LOGITS
    eering
    0.87
     laureate
    0.82
     Seym
    0.81
    ocracy
    0.79
    ocrat
    0.79
     republic
    0.79
     democracy
    0.75
     droid
    0.74
     democr
    0.74
    democracy
    0.74
    Act Density 0.012%

    No Known Activations