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

    Neuronpedia

    INDEX
    Explanations

    locations or geographical areas within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inn
    -0.78
    enstein
    -0.78
    gling
    -0.75
    glers
    -0.73
    rating
    -0.73
    lett
    -0.73
    icial
    -0.71
    gins
    -0.71
    Cert
    -0.70
    ined
    -0.69
    POSITIVE LOGITS
     vicinity
    1.04
     surrounding
    1.02
     area
    1.00
     adjoining
    0.91
     bounded
    0.87
     adjacent
    0.86
     areas
    0.82
     periphery
    0.79
     perimeter
    0.77
     nearest
    0.76
    Act Density 0.053%

    No Known Activations