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

    Neuronpedia

    INDEX
    Explanations

    locations or geographic references

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations and names, particularly 'Dundee' and 'Aberdeen'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-
    -0.82
    trop
    -0.79
    =-=-=-=-=-=-=-=-
    -0.73
     Khe
    -0.72
    pering
    -0.71
    ographed
    -0.68
    âĸ¬
    -0.67
    portation
    -0.67
    @@@@@@@@
    -0.67
    opsis
    -0.66
    POSITIVE LOGITS
     Aberdeen
    1.00
    deen
    0.93
     Dund
    0.88
    iband
    0.85
    imore
    0.83
    yip
    0.81
    minster
    0.78
    urst
    0.78
    lain
    0.77
    yrinth
    0.77
    Act Density 0.023%

    No Known Activations