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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Indian."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entai
    -0.16
    _marshall
    -0.16
    tainment
    -0.15
    olon
    -0.15
    inger
    -0.15
    iri
    -0.15
    ibold
    -0.15
    inator
    -0.15
    먼
    -0.14
    tier
    -0.14
    POSITIVE LOGITS
    apolis
    0.36
     Ocean
    0.25
    Ocean
    0.20
     ÄIJá»Ļ
    0.20
    OLA
    0.19
    ola
    0.18
    apol
    0.18
    à¹ģà¸Ķà¸ĩ
    0.18
     Wells
    0.17
    ania
    0.16
    Act Density 0.010%

    No Known Activations