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

    Neuronpedia

    INDEX
    Explanations

    locations or entities related to North America

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rative
    -0.80
    ration
    -0.72
    ILA
    -0.70
    imental
    -0.68
    ulous
    -0.67
    FAULT
    -0.67
    xxxxxxxx
    -0.67
    TED
    -0.66
    NRS
    -0.66
    ername
    -0.66
    POSITIVE LOGITS
    ampton
    1.24
     Carolina
    1.18
    western
    1.06
     Korea
    1.06
     Pole
    1.04
     Dakota
    1.04
    west
    0.97
    shore
    0.96
     Koreans
    0.95
    umber
    0.93
    Act Density 0.027%

    No Known Activations