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

    Neuronpedia

    INDEX
    Explanations

    references to neighboring countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "neighboring" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -0.93
    endi
    -0.85
    odor
    -0.80
    ueller
    -0.77
    anwhile
    -0.76
    istry
    -0.76
    trak
    -0.76
    unker
    -0.76
    ocker
    -0.74
    util
    -0.73
    POSITIVE LOGITS
     territories
    0.92
     Territories
    0.90
     countries
    0.90
     neighbor
    0.90
     neighbors
    0.88
     Borders
    0.83
     nations
    0.83
     provinces
    0.82
     regions
    0.82
     neighboring
    0.82
    Act Density 0.020%

    No Known Activations