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

    Neuronpedia

    INDEX
    Explanations

    locations or place names related to cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations, particularly cities and towns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hens
    -0.73
    atile
    -0.72
    cess
    -0.72
    gs
    -0.67
    ches
    -0.67
    CE
    -0.66
    nings
    -0.65
    ONSORED
    -0.65
    gue
    -0.64
    anity
    -0.64
    POSITIVE LOGITS
     Auckland
    0.93
    £ı
    0.85
     Zealand
    0.84
    uckland
    0.81
    Ń·
    0.78
    ĵĺ
    0.77
     Canterbury
    0.76
    church
    0.75
    stown
    0.71
    olulu
    0.70
    Act Density 0.007%

    No Known Activations