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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations or hometowns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allest
    -0.17
    ofi
    -0.15
    uraa
    -0.15
     Depths
    -0.15
    linik
    -0.14
    otten
    -0.14
    wand
    -0.14
    paged
    -0.14
    ettel
    -0.14
    airo
    -0.14
    POSITIVE LOGITS
     native
    0.49
     home
    0.45
     hometown
    0.43
    native
    0.39
     homeland
    0.38
     adopted
    0.38
     birth
    0.37
     adopt
    0.34
    -native
    0.34
     stom
    0.33
    Act Density 0.142%

    No Known Activations