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

    Neuronpedia

    INDEX
    Explanations

    references to pork

    oai_token-act-pair · gpt-3.5-turbo

    references to pork

    oai_token-act-pair · gpt-4-turbo

    mentions of pork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Occupations
    -0.82
    IFE
    -0.73
    EMBER
    -0.73
     Stanton
    -0.73
    DCS
    -0.71
     Insp
    -0.70
     Standing
    -0.70
     Younger
    -0.70
    âĸ¬
    -0.70
    Downloadha
    -0.68
    POSITIVE LOGITS
    bean
    1.03
     belly
    1.01
     chops
    0.95
     pork
    0.90
    meat
    0.89
     chop
    0.87
     roast
    0.81
    seed
    0.81
    hao
    0.81
     sausage
    0.81
    Act Density 0.011%

    No Known Activations