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

    Neuronpedia

    INDEX
    Explanations

    references to socioeconomic status and its effects on groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esub
    -0.15
    rates
    -0.15
    па
    -0.15
    enburg
    -0.15
    urga
    -0.14
    ADER
    -0.14
    AtPath
    -0.14
     Patterson
    -0.14
    askell
    -0.14
    êu
    -0.14
    POSITIVE LOGITS
     quart
    0.35
     Quart
    0.32
     median
    0.30
    iles
    0.30
     med
    0.29
    ile
    0.29
     Median
    0.28
     percentile
    0.28
    median
    0.27
     quant
    0.25
    Act Density 0.066%

    No Known Activations