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

    Neuronpedia

    INDEX
    Explanations

    locations and geographical regions

    oai_token-act-pair · gpt-3.5-turbo

    geographic regions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.80
    itness
    -0.78
    taker
    -0.71
     councillor
    -0.70
     gard
    -0.69
     shovel
    -0.68
     pun
    -0.67
    itor
    -0.67
     deeds
    -0.67
     bom
    -0.66
    POSITIVE LOGITS
     Asia
    1.66
     Africa
    1.47
    Asia
    1.46
     Europe
    1.33
     Euras
    1.28
     Caucasus
    1.21
     continents
    1.20
     Americas
    1.20
     Balkans
    1.18
     Latin
    1.18
    Act Density 0.260%

    No Known Activations