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

    Neuronpedia

    INDEX
    Explanations

    references to diverse ethnic and national identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urret
    -0.15
    yn
    -0.15
    urre
    -0.15
    ourg
    -0.15
    etus
    -0.15
    تص
    -0.15
     Españ
    -0.15
    Ùģات
    -0.14
    pec
    -0.14
    ÅĽcie
    -0.14
    POSITIVE LOGITS
    -born
    0.34
    born
    0.30
     born
    0.30
    -Americans
    0.26
    -American
    0.26
     nationals
    0.26
     exp
    0.25
    -desc
    0.21
     who
    0.21
     Nationals
    0.21
    Act Density 0.089%

    No Known Activations