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

    Neuronpedia

    INDEX
    Explanations

    mentions of various types of clothing, particularly dresses

    oai_token-act-pair · gpt-3.5-turbo

    references to "dress" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntil
    -0.85
     Blessed
    -0.80
    interrupted
    -0.77
    ilver
    -0.66
     Cursed
    -0.65
    ounding
    -0.64
    JV
    -0.64
    elected
    -0.63
     Fired
    -0.62
    ocalyptic
    -0.61
    POSITIVE LOGITS
     gown
    1.09
     dresses
    1.08
     dress
    1.02
     shoes
    1.01
    pants
    0.96
     apparel
    0.95
     attire
    0.94
    glers
    0.94
     rehearsal
    0.91
     Dress
    0.90
    Act Density 0.007%

    No Known Activations