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

    Neuronpedia

    INDEX
    Explanations

    mentions of different cuts of meat, particularly pork

    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
     Occupations
    -0.81
     Insp
    -0.78
     Standing
    -0.75
    EMBER
    -0.75
     Stanton
    -0.74
    DCS
    -0.73
    âĸ¬
    -0.71
    pmwiki
    -0.69
     Younger
    -0.69
    ASED
    -0.69
    POSITIVE LOGITS
     pork
    1.15
     belly
    1.05
    bean
    1.04
     chops
    0.99
    meat
    0.96
     chop
    0.94
    pie
    0.91
     roast
    0.89
     pies
    0.89
    fruit
    0.86
    Act Density 0.006%

    No Known Activations