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

    Neuronpedia

    INDEX
    Explanations

    mentions of the United Kingdom (UK) in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to the UK

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rods
    -0.69
     Shots
    -0.67
    iquid
    -0.67
     packets
    -0.64
    BOOK
    -0.62
    addock
    -0.62
    afort
    -0.62
    åħī
    -0.61
    ãĥĬ
    -0.61
    м
    -0.61
    POSITIVE LOGITS
    istani
    0.98
     Airways
    0.78
    mare
    0.74
    rain
    0.72
     Embassy
    0.71
     Columb
    0.69
    raine
    0.69
    orea
    0.68
    ernel
    0.67
    umar
    0.67
    Act Density 0.025%

    No Known Activations