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

    Neuronpedia

    INDEX
    Explanations

    categories and affiliations related to nationalities and professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vueltas
    -0.52
     itſelf
    -0.48
    ähteet
    -0.47
     místa
    -0.46
     parfüm
    -0.46
     kväll
    -0.46
    hdessä
    -0.46
     typelib
    -0.46
     ilustración
    -0.45
     adelante
    -0.44
    POSITIVE LOGITS
     Mexican
    1.02
     Canadian
    0.99
     Chinese
    0.98
    Mexican
    0.98
     Indian
    0.98
     German
    0.98
     Australian
    0.97
     Italian
    0.97
     American
    0.96
    Canadian
    0.95
    Act Density 0.699%

    No Known Activations