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

    Neuronpedia

    INDEX
    Explanations

    locations or geographic areas

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or regions identified as "area."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.90
    inn
    -0.81
    kus
    -0.77
    ccording
    -0.77
    ilts
    -0.74
    artz
    -0.72
    guided
    -0.72
    sonian
    -0.72
    ined
    -0.71
    ining
    -0.70
    POSITIVE LOGITS
     area
    1.11
     areas
    1.01
    area
    0.88
     Area
    0.82
    cules
    0.81
     Areas
    0.80
     locality
    0.76
     rug
    0.76
     vicinity
    0.71
    stones
    0.68
    Act Density 0.025%

    No Known Activations