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

    Neuronpedia

    INDEX
    Explanations

    references to racial issues and disparities in the context of legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.73
    reetings
    -0.72
     Centauri
    -0.71
    Widget
    -0.71
    Quantity
    -0.69
    Dialog
    -0.68
    ibli
    -0.67
    sg
    -0.66
    zees
    -0.65
    Reading
    -0.64
    POSITIVE LOGITS
     subsequently
    1.14
     blamed
    1.10
     controvers
    1.05
     unsuccessfully
    1.04
     later
    0.99
     resulted
    0.97
     famously
    0.97
     pressured
    0.94
     ensuing
    0.94
     sued
    0.93
    Act Density 0.580%

    No Known Activations