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

    Neuronpedia

    INDEX
    Explanations

    mentions of pork products

    oai_token-act-pair · gpt-3.5-turbo

    references to pork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.80
     Stanton
    -0.78
    DCS
    -0.76
    EMBER
    -0.75
     SCHOOL
    -0.70
     Insp
    -0.70
    uminati
    -0.68
    âĸ¬
    -0.68
    EMP
    -0.67
    idges
    -0.67
    POSITIVE LOGITS
     belly
    1.09
    meat
    1.01
    bean
    0.98
     chops
    0.92
     roast
    0.91
     chop
    0.86
    sty
    0.85
     pork
    0.85
     barrel
    0.82
     sausage
    0.79
    Act Density 0.012%

    No Known Activations