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

    Neuronpedia

    INDEX
    Explanations

    proper nouns indicating a person's birthplace

    oai_token-act-pair · gpt-3.5-turbo

    references to people’s places of birth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phis
    -0.98
    phasis
    -0.94
    awaru
    -0.86
    qqa
    -0.80
    olicy
    -0.80
    raviolet
    -0.77
    eredith
    -0.76
    uyomi
    -0.76
    ivably
    -0.74
    erguson
    -0.74
    POSITIVE LOGITS
    ness
    0.85
    lings
    0.80
    nesses
    0.79
    born
    0.74
    ling
    0.70
    aways
    0.69
    iste
    0.68
    stellar
    0.66
     abroad
    0.65
    éļ
    0.64
    Act Density 0.023%

    No Known Activations