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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    the word "located," indicating references to geographical locations or placements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -1.06
    ework
    -0.95
    nature
    -0.82
    haw
    -0.80
    eries
    -0.80
    air
    -0.79
    airs
    -0.78
    ned
    -0.77
    qs
    -0.77
    rendered
    -0.76
    POSITIVE LOGITS
    uate
    0.82
     geographically
    0.76
     locations
    0.72
     centrally
    0.70
     nearest
    0.69
     Aires
    0.69
     located
    0.68
     location
    0.67
     downtown
    0.67
     locality
    0.66
    Act Density 0.033%

    No Known Activations