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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names, particularly the name "Boris"

    oai_token-act-pair · gpt-3.5-turbo

    references to Boris Johnson and his political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imil
    -0.76
    lessly
    -0.72
    uate
    -0.68
    ening
    -0.68
    imony
    -0.67
    tenance
    -0.66
    inez
    -0.64
    lessness
    -0.63
    oning
    -0.62
    ily
    -0.61
    POSITIVE LOGITS
    cair
    0.81
    enty
    0.80
    ensibly
    0.78
    adier
    0.76
    bledon
    0.75
    rer
    0.74
    ovich
    0.73
    cot
    0.72
     Soup
    0.72
    arettes
    0.72
    Act Density 0.125%

    No Known Activations