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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the term "sub-" indicating subcategories or subordinate elements within a broader context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reed
    -0.75
     Kis
    -0.74
     Dickinson
    -0.74
     Sanford
    -0.74
     Zup
    -0.74
    ulhu
    -0.74
     Cassidy
    -0.73
     Hopkins
    -0.72
     Kenny
    -0.72
     Meadows
    -0.72
    POSITIVE LOGITS
    dimensional
    1.20
    sized
    1.11
    optim
    1.04
    prime
    1.04
    issue
    1.03
    commun
    1.03
    division
    1.03
    powered
    1.02
    surface
    1.01
    liter
    1.01
    Act Density 0.066%

    No Known Activations