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

    Neuronpedia

    INDEX
    Explanations

    references to personal origins and cultural backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trak
    -0.16
    anson
    -0.16
    дов
    -0.15
    elper
    -0.15
    idar
    -0.15
    ripp
    -0.15
    angler
    -0.14
    GLOBALS
    -0.14
    _rwlock
    -0.14
    à¹Ģà¸Ĺ
    -0.14
    POSITIVE LOGITS
     hometown
    0.34
     native
    0.33
     homeland
    0.30
     home
    0.29
     birth
    0.27
    ometown
    0.24
    -native
    0.24
    native
    0.23
     origin
    0.23
     natives
    0.22
    Act Density 0.143%

    No Known Activations