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

    Neuronpedia

    INDEX
    Explanations

    references to nationalities and local identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lix
    -0.16
    gings
    -0.15
    ä¸Ńåľĭ
    -0.14
    bidden
    -0.14
    æĿ¥èĩª
    -0.14
     reput
    -0.14
     chinese
    -0.14
     United
    -0.14
    alling
    -0.14
     latina
    -0.13
    POSITIVE LOGITS
    -American
    0.39
    -speaking
    0.32
    -Americans
    0.31
    -Russian
    0.31
    -language
    0.29
    -born
    0.26
    -Israel
    0.26
    ischer
    0.24
    apolis
    0.24
    -flag
    0.23
    Act Density 0.257%

    No Known Activations