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

    Neuronpedia

    INDEX
    Explanations

    paintings or references to paintings

    oai_token-act-pair · gpt-3.5-turbo

    references to paintings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nir
    -0.77
    reme
    -0.76
    uli
    -0.75
    cgi
    -0.73
    Ïī
    -0.71
    reek
    -0.71
    aucus
    -0.71
    indal
    -0.69
    ornia
    -0.69
    aspx
    -0.69
    POSITIVE LOGITS
     painter
    1.16
     paintings
    1.12
     painting
    1.12
     depicting
    1.03
     Painting
    0.94
     portraits
    0.93
    isans
    0.90
     paints
    0.89
     artwork
    0.88
     painted
    0.87
    Act Density 0.014%

    No Known Activations