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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming functions and methods

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to programming and software functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staff
    -0.71
    Brexit
    -0.71
    scar
    -0.70
    atti
    -0.69
    egal
    -0.69
    united
    -0.68
    toe
    -0.68
    soType
    -0.66
    liv
    -0.66
    iola
    -0.66
    POSITIVE LOGITS
     automatically
    1.03
     specified
    0.96
     initialization
    0.92
     arbitrary
    0.89
     whichever
    0.88
     parameters
    0.88
     notifications
    0.88
     random
    0.87
     variables
    0.86
     incoming
    0.85
    Act Density 0.229%

    No Known Activations