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

    Neuronpedia

    INDEX
    Explanations

    references to various types of clothing, with a strong preference for the word 'coat'

    oai_token-act-pair · gpt-3.5-turbo

    references to coats and jackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KNOWN
    -0.69
    FER
    -0.69
    ENE
    -0.68
    quist
    -0.68
    icts
    -0.67
    erent
    -0.67
    iates
    -0.66
    iating
    -0.65
    chuk
    -0.64
    Refer
    -0.61
    POSITIVE LOGITS
     coat
    0.96
     tails
    0.96
     sleeves
    0.93
     jacket
    0.92
     sleeve
    0.88
    pins
    0.87
     worn
    0.84
     wearer
    0.83
    hair
    0.81
    maker
    0.81
    Act Density 0.043%

    No Known Activations