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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating physical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ework
    -0.74
    sequence
    -0.73
    rendered
    -0.71
    spir
    -0.69
    ned
    -0.69
    vous
    -0.68
    ese
    -0.67
    eries
    -0.66
    airs
    -0.66
    doms
    -0.65
    POSITIVE LOGITS
    uate
    1.00
     atop
    0.97
     geographically
    0.96
     near
    0.95
     smack
    0.94
     somewhere
    0.92
     centrally
    0.89
     squarely
    0.86
     downtown
    0.85
     beneath
    0.84
    Act Density 0.061%

    No Known Activations