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

    Neuronpedia

    INDEX
    Explanations

    words related to specific locations, possibly focusing on government or politics

    oai_token-act-pair · gpt-3.5-turbo

    names of countries or places, especially those that end with 'ador' or are specifically about Brunei and El Salvador

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardy
    -0.82
    quartered
    -0.71
     pity
    -0.66
    eding
    -0.64
    sheet
    -0.61
     CST
    -0.60
    ples
    -0.60
     premise
    -0.60
    IME
    -0.59
     clipboard
    -0.59
    POSITIVE LOGITS
    ably
    0.94
    ians
    0.88
    ÃŃa
    0.85
    abil
    0.84
    ador
    0.83
    hyde
    0.82
    idad
    0.81
    illo
    0.80
    neau
    0.79
    pour
    0.76
    Act Density 0.019%

    No Known Activations