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

    Neuronpedia

    INDEX
    Explanations

    references to race, specifically the terms related to "whites" and "blacks."

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

    whites and blacks discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mik
    -0.54
    [
    -0.52
     Py
    -0.52
    ,
    -0.48
    -
    -0.47
     Pin
    -0.47
     Pe
    -0.47
     Kam
    -0.46
     nutri
    -0.45
     Van
    -0.45
    POSITIVE LOGITS
     Whites
    1.42
    Whites
    1.38
     whites
    1.36
    whites
    1.13
     Blacks
    0.91
     blacks
    0.91
     highs
    0.76
     reds
    0.72
    ambién
    0.66
     desmotivaciones
    0.66
    Act Density 0.014%

    No Known Activations