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

    Neuronpedia

    INDEX
    Explanations

    mentions of London and its associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    })$}
    -0.93
     OGSÅ
    -0.93
     obstante
    -0.86
    makeConstraints
    -0.82
     }}$}
    -0.81
     ویکی‌آمباردا
    -0.81
     Hust
    -0.79
     Ã
    -0.79
    łaś
    -0.78
    stalgia
    -0.78
    POSITIVE LOGITS
     London
    1.05
    London
    0.94
     Londres
    0.92
     LONDON
    0.86
    widetilde
    0.85
    derry
    0.84
     london
    0.83
    Boas
    0.82
    Londres
    0.82
     Montero
    0.81
    Act Density 0.115%

    No Known Activations