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

    Neuronpedia

    INDEX
    Explanations

    references to socioeconomic class, specifically the middle class

    oai_token-act-pair · gpt-3.5-turbo

    references to social class or socioeconomic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rem
    -0.69
     patience
    -0.66
     receipts
    -0.65
     solicit
    -0.65
    areth
    -0.65
     drip
    -0.63
     undert
    -0.62
     solic
    -0.61
     exh
    -0.60
     fertil
    -0.59
    POSITIVE LOGITS
    class
    4.27
    classes
    2.81
    Class
    2.61
     class
    2.40
    CLASS
    2.12
     CLASS
    2.09
     Class
    2.07
     Classes
    1.79
     classes
    1.78
     subclass
    1.65
    Act Density 0.015%

    No Known Activations