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

    Neuronpedia

    INDEX
    Explanations

    references to countries and their relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Berlín
    -0.72
     Chartres
    -0.70
     Milán
    -0.69
     serr
    -0.67
     Ripper
    -0.65
     FEES
    -0.64
     américains
    -0.64
     frontale
    -0.63
     stole
    -0.61
     Liens
    -0.61
    POSITIVE LOGITS
     Country
    1.39
     country
    1.35
     countries
    1.32
     COUNTRY
    1.32
     Countries
    1.27
    countries
    1.26
    Countries
    1.20
    Country
    1.17
    COUNTRY
    1.17
    country
    1.16
    Act Density 0.037%

    No Known Activations