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

    Neuronpedia

    INDEX
    Explanations

    geographical locations, particularly cities

    oai_token-act-pair · gpt-3.5-turbo

    mention of specific geographical locations, particularly cities in Scotland

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OHN
    -0.81
    ocre
    -0.76
    aceous
    -0.74
    riv
    -0.71
    ramid
    -0.71
    baugh
    -0.67
    eus
    -0.67
    heses
    -0.66
    pees
    -0.66
    bda
    -0.66
    POSITIVE LOGITS
     Lumpur
    1.01
    shire
    0.94
    inburgh
    0.90
     Glasgow
    0.80
     Airport
    0.79
     Disneyland
    0.77
    é¾įåĸļ士
    0.73
    gow
    0.72
     Harbour
    0.72
     Ports
    0.72
    Act Density 0.025%

    No Known Activations