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

    Neuronpedia

    INDEX
    Explanations

    mentions of costumes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of costumes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.75
    tical
    -0.71
    avanaugh
    -0.69
    ntil
    -0.69
     Hes
    -0.63
    utherford
    -0.63
    eph
    -0.63
    minist
    -0.62
    fram
    -0.62
    20439
    -0.60
    POSITIVE LOGITS
     costumes
    1.27
     costume
    1.26
     Costume
    1.05
     attire
    0.90
     wardrobe
    0.83
     apparel
    0.82
     gown
    0.82
     jewelry
    0.80
     gloves
    0.79
    pole
    0.79
    Act Density 0.008%

    No Known Activations