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

    Neuronpedia

    INDEX
    Explanations

    references to racial and ethnic representation and diversity issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.83
    ChildScrollView
    -0.78
    Биография
    -0.76
    RegressionTest
    -0.73
    )++;
    -0.73
     externi
    -0.72
    YourGuide
    -0.72
     surla
    -0.72
    elemField
    -0.71
    Bisous
    -0.70
    POSITIVE LOGITS
     racial
    0.60
     ethnicity
    0.59
     minority
    0.57
     ethnic
    0.57
     male
    0.53
     minorities
    0.52
     aren
    0.51
     racially
    0.49
     gay
    0.48
     berk
    0.48
    Act Density 0.292%

    No Known Activations