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

    Neuronpedia

    INDEX
    Explanations

    instances and references to prejudice in various contexts

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

    prejudice and its effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓘ
    -0.57
    
    -0.55
     Rptr
    -0.53
    Governor
    -0.51
    хьтан
    -0.50
    verwijspagina
    -0.50
     Uniwers
    -0.48
     AssemblyCulture
    -0.48
    telles
    -0.48
    Opéra
    -0.47
    POSITIVE LOGITS
     prejudice
    2.00
     Prejudice
    1.82
     prejudices
    1.60
     prejudiced
    1.49
    judice
    1.41
     preju
    1.21
     prejudicial
    1.11
     pregi
    0.95
     prejud
    0.94
     bias
    0.66
    Act Density 0.007%

    No Known Activations