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

    Neuronpedia

    INDEX
    Explanations

    geographical locations or borders

    oai_token-act-pair · gpt-3.5-turbo

    empty tokens or breaks within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.88
     DeV
    -0.76
    asonable
    -0.70
    aroo
    -0.68
     Darrell
    -0.67
     Vaughn
    -0.65
    Doc
    -0.62
     shenan
    -0.61
    uum
    -0.60
    Keefe
    -0.60
    POSITIVE LOGITS
     Nato
    1.17
     abroad
    1.04
     UNESCO
    1.03
     exports
    1.01
     imports
    0.99
     NATO
    0.96
     export
    0.94
     imperialist
    0.93
     repatri
    0.92
     foreigners
    0.90
    Act Density 1.330%

    No Known Activations