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

    Neuronpedia

    INDEX
    Explanations

    descriptions of paintings and their values

    oai_token-act-pair · gpt-3.5-turbo

    references to paintings and artwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DN
    -0.88
    iott
    -0.76
    aucus
    -0.74
    unker
    -0.74
    lower
    -0.73
    ularity
    -0.72
    orsi
    -0.71
    inki
    -0.71
    vernment
    -0.69
    ldon
    -0.68
    POSITIVE LOGITS
     painter
    1.30
     paintings
    1.25
     portraits
    1.20
     depicting
    1.20
     portrait
    1.18
     painting
    1.16
     artwork
    1.15
     mural
    1.12
     gallery
    1.00
     Painting
    1.00
    Act Density 0.067%

    No Known Activations