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

    Neuronpedia

    INDEX
    Explanations

    mentions of clothing or items worn by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wearing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edia
    -0.85
    uddin
    -0.70
    deal
    -0.68
    MQ
    -0.68
    =-=-=-=-
    -0.68
    ISO
    -0.64
    estine
    -0.64
    Publisher
    -0.64
    DL
    -0.64
    article
    -0.63
    POSITIVE LOGITS
     worn
    1.14
     wearer
    1.02
     apparel
    1.02
     clothing
    0.98
     jeans
    0.94
     wear
    0.92
     shoes
    0.90
     robes
    0.88
     uniforms
    0.87
     clothes
    0.86
    Act Density 0.014%

    No Known Activations