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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and regions

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sworth
    -0.78
    RES
    -0.77
    erity
    -0.75
    rators
    -0.73
    AMI
    -0.72
    STD
    -0.70
    iage
    -0.69
    ACY
    -0.67
    OPS
    -0.67
    pson
    -0.67
    POSITIVE LOGITS
     Caucasus
    1.31
     Balkans
    1.30
     Alps
    1.29
     Mediterranean
    1.22
     peninsula
    1.22
     Continent
    1.19
     Kingdoms
    1.19
     Isles
    1.18
     plains
    1.17
     coasts
    1.15
    Act Density 0.231%

    No Known Activations