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

    Neuronpedia

    INDEX
    Explanations

    mentions of soy and related products

    oai_token-act-pair · gpt-3.5-turbo

    references to soy products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Imran
    -0.75
     Gunn
    -0.73
     Sins
    -0.73
     Guardians
    -0.68
    GBT
    -0.66
     Alexandria
    -0.66
     Humanity
    -0.65
     Wonderland
    -0.64
     Learned
    -0.64
     Jav
    -0.63
    POSITIVE LOGITS
    bean
    1.94
    beans
    1.94
    food
    1.17
     milk
    1.13
     beans
    1.06
     sauce
    1.05
    meal
    1.02
    mil
    1.01
    seed
    0.98
     bean
    0.96
    Act Density 0.045%

    No Known Activations