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

    Neuronpedia

    INDEX
    Explanations

    references to commands or requests

    oai_token-act-pair · gpt-3.5-turbo

    questions and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fiscal
    -0.82
     Ninth
    -0.79
    Physical
    -0.78
    Mobil
    -0.77
     Canaver
    -0.76
     Clause
    -0.76
    Component
    -0.75
     Parish
    -0.74
     Subcommittee
    -0.74
    Thirty
    -0.74
    POSITIVE LOGITS
     english
    1.23
     dont
    1.17
     doesnt
    1.05
     americ
    1.05
     didnt
    1.03
     david
    1.03
     lol
    1.02
     alot
    0.97
     haha
    0.96
     pics
    0.90
    Act Density 0.963%

    No Known Activations