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

    Neuronpedia

    INDEX
    Explanations

    words related to people's places of birth

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' places of origin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phis
    -1.02
    phasis
    -0.94
    qqa
    -0.89
    raviolet
    -0.86
    awaru
    -0.84
    dfx
    -0.80
    eredith
    -0.78
    uyomi
    -0.78
     tiss
    -0.78
    awks
    -0.76
    POSITIVE LOGITS
    lings
    0.87
    born
    0.83
    ness
    0.82
    nesses
    0.75
    iste
    0.74
    smith
    0.74
     Cub
    0.71
    ãĥĥãĥī
    0.70
    sworth
    0.70
    liest
    0.68
    Act Density 0.018%

    No Known Activations