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

    Neuronpedia

    INDEX
    Explanations

    references to ethnic minority groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    minority groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ram
    -0.42
    launch
    -0.41
     Appl
    -0.40
     tourne
    -0.39
     plan
    -0.39
     Wel
    -0.39
     easy
    -0.39
     quoi
    -0.39
     Eng
    -0.38
     राम
    -0.38
    POSITIVE LOGITS
     minority
    2.33
     Minority
    2.08
     minorities
    1.87
    ority
    1.55
    少数
    1.15
     MINOR
    0.88
     Minder
    0.84
     Majority
    0.79
    Majority
    0.79
    Personendaten
    0.75
    Act Density 0.008%

    No Known Activations