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

    Neuronpedia

    INDEX
    Explanations

    mentions of the city London

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "London."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >>>>>>>>
    -0.72
    ACA
    -0.72
     kernels
    -0.70
     "$:/
    -0.70
    ono
    -0.69
    checks
    -0.68
    irez
    -0.65
    weapon
    -0.65
    $$
    -0.64
    }}}
    -0.63
    POSITIVE LOGITS
     London
    3.54
    London
    3.24
     Edinburgh
    1.96
     Dublin
    1.91
     Britain
    1.89
     Glasgow
    1.88
    ONDON
    1.87
     Westminster
    1.80
     Paris
    1.79
     Berlin
    1.79
    Act Density 0.015%

    No Known Activations