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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programs and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to food-related programs and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Norris
    -0.76
     Burr
    -0.75
     Hamb
    -0.75
     Cotton
    -0.73
     Vaughan
    -0.71
     Horowitz
    -0.70
     Burnett
    -0.70
     Hague
    -0.70
     Chambers
    -0.69
     Dickinson
    -0.69
    POSITIVE LOGITS
    based
    1.38
    related
    1.35
    derived
    1.26
    friendly
    1.26
    themed
    1.21
    centric
    1.19
    induced
    1.19
    oriented
    1.17
    driven
    1.16
    operated
    1.15
    Act Density 0.166%

    No Known Activations