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

    Neuronpedia

    INDEX
    Explanations

    locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations, particularly cities and their relation to events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haar
    -0.91
    enegger
    -0.82
    eal
    -0.77
    ographed
    -0.73
    Mach
    -0.68
    alez
    -0.67
    rained
    -0.66
    orter
    -0.65
    venge
    -0.64
    ternity
    -0.64
    POSITIVE LOGITS
     City
    0.97
     Yard
    0.91
     Harbour
    0.91
     Swansea
    0.89
     Borough
    0.85
     Harbor
    0.85
     harbour
    0.85
    sburg
    0.81
     Township
    0.79
    shire
    0.77
    Act Density 0.014%

    No Known Activations