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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location, specifically "Sydney"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Sydney

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OHN
    -0.85
    aired
    -0.81
    Magikarp
    -0.78
    toggle
    -0.76
    arist
    -0.76
    abet
    -0.74
    aid
    -0.73
    ocobo
    -0.73
    Torrent
    -0.72
    inelli
    -0.70
    POSITIVE LOGITS
     Harbour
    1.11
     Lumpur
    1.08
     NSW
    0.83
    ites
    0.81
     Harbor
    0.81
     Morning
    0.81
     Sydney
    0.79
     Brisbane
    0.79
     Opera
    0.74
     Turnbull
    0.73
    Act Density 0.007%

    No Known Activations