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

    Neuronpedia

    INDEX
    Explanations

    references to countries and their hierarchies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chartres
    -0.84
     Berlín
    -0.77
     Milán
    -0.75
     serr
    -0.74
     Ripper
    -0.68
     frontale
    -0.66
     tremp
    -0.65
     Asparagus
    -0.64
     asparagus
    -0.64
     Yorkers
    -0.63
    POSITIVE LOGITS
     Country
    1.28
     countries
    1.26
     country
    1.24
     COUNTRY
    1.23
     Countries
    1.20
    countries
    1.19
    Countries
    1.12
    COUNTRY
    1.08
    Country
    1.05
    country
    1.04
    Act Density 0.034%

    No Known Activations