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

    Neuronpedia

    INDEX
    Explanations

    references to painting objects or surfaces

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "painted" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMY
    -0.85
    PF
    -0.79
    EMS
    -0.74
    aucus
    -0.72
    cum
    -0.71
    idem
    -0.70
    ffic
    -0.70
    HI
    -0.68
    ML
    -0.65
    CVE
    -0.65
    POSITIVE LOGITS
     painted
    1.33
     painting
    1.08
    painted
    1.06
     paints
    1.02
     decoration
    0.96
     painter
    0.91
     depicting
    0.91
    escription
    0.89
     paint
    0.89
     markings
    0.88
    Act Density 0.007%

    No Known Activations