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

    Neuronpedia

    INDEX
    Explanations

    references to various types of beans

    oai_token-act-pair · gpt-3.5-turbo

    references to beans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NR
    -0.80
     TN
    -0.75
     Spectre
    -0.73
    phys
    -0.73
     FN
    -0.70
     DV
    -0.69
    ulation
    -0.69
    TN
    -0.68
    vi
    -0.68
    Spect
    -0.67
    POSITIVE LOGITS
     beans
    3.94
     Beans
    3.37
     bean
    3.23
     Bean
    2.75
    beans
    2.69
    bean
    2.17
     peas
    1.57
     pods
    1.36
     roast
    1.27
     tomatoes
    1.26
    Act Density 0.030%

    No Known Activations