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

    Neuronpedia

    INDEX
    Explanations

    references to being treated as inferior or second-class in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to social class distinctions and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bats
    -0.63
    IUM
    -0.62
     MEN
    -0.62
     HUN
    -0.61
    owe
    -0.60
    GUI
    -0.59
    Sah
    -0.58
    thirst
    -0.57
    kees
    -0.57
    iland
    -0.56
    POSITIVE LOGITS
    imester
    1.00
    endment
    0.87
    agonist
    0.69
    uctor
    0.68
    eve
    0.67
    amic
    0.66
     onwards
    0.66
    ttle
    0.65
     choke
    0.64
     bidder
    0.63
    Act Density 0.124%

    No Known Activations