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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to racial identity and privilege

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.75
    HostException
    -0.73
    Portale
    -0.71
     ſeveral
    -0.69
    ViewImports
    -0.65
    BufferException
    -0.62
     Exposed
    -0.61
     raiſ
    -0.59
     שוליים
    -0.59
     Anſ
    -0.58
    POSITIVE LOGITS
    出版年
    0.61
    Zacks
    0.56
    AddTagHelper
    0.53
    APOLIS
    0.50
     Roskov
    0.47
    0.45
    norm
    0.44
    XHR
    0.43
    AFX
    0.43
    couvrir
    0.43
    Act Density 0.055%

    No Known Activations