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

    Neuronpedia

    INDEX
    Explanations

    locations or places near a specific point

    oai_token-act-pair · gpt-3.5-turbo

    references to locations with the word "near."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilus
    -0.83
    Percent
    -0.75
    BILL
    -0.75
    Upload
    -0.73
    alian
    -0.71
    UX
    -0.71
    azeera
    -0.69
    Wire
    -0.69
    glers
    -0.69
    ÑĮ
    -0.68
    POSITIVE LOGITS
    sighted
    0.89
    shore
    0.86
     Bethlehem
    0.80
     misses
    0.80
     Vancouver
    0.77
     Fresno
    0.77
     Philadelphia
    0.74
     Mount
    0.72
     campus
    0.72
     vicinity
    0.72
    Act Density 0.028%

    No Known Activations