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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "UK"

    oai_token-act-pair · gpt-3.5-turbo

    references to the United Kingdom or related abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGR
    -0.69
     actionGroup
    -0.66
    acted
    -0.64
    Flight
    -0.64
    æ³
    -0.63
     lapse
    -0.62
    ONY
    -0.61
    staking
    -0.60
    BOOK
    -0.60
     wards
    -0.59
    POSITIVE LOGITS
    ulkan
    1.32
    raine
    1.05
    umar
    1.04
    ileaks
    1.03
    eness
    1.01
    ovych
    0.99
    hov
    0.93
    erala
    0.91
    uru
    0.90
    akis
    0.89
    Act Density 0.016%

    No Known Activations