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

    Neuronpedia

    INDEX
    Explanations

    statistical and numerical differences within social issues, especially concerning racial disparities and political polling data

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Juf
    -0.80
     Ruman
    -0.80
     Manufact
    -0.79
     Guel
    -0.76
     philanth
    -0.76
     inev
    -0.76
     secon
    -0.74
     Khart
    -0.72
     volunte
    -0.71
     Sted
    -0.71
    POSITIVE LOGITS
     difference
    0.73
    difference
    0.69
     differences
    0.64
    AddTagHelper
    0.61
     Δ
    0.60
    awtextra
    0.58
     Difference
    0.57
     margin
    0.56
     diferença
    0.55
    margin
    0.55
    Act Density 0.364%

    No Known Activations