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

    Neuronpedia

    INDEX
    Explanations

    elements related to configuration and data handling in software development contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anford
    -0.18
    amburg
    -0.16
    alez
    -0.16
    .componentInstance
    -0.15
    UTIL
    -0.15
    elpers
    -0.14
    upal
    -0.14
    utils
    -0.14
    uitka
    -0.14
    Misc
    -0.13
    POSITIVE LOGITS
    Mode
    0.29
    mode
    0.24
    _mode
    0.22
    Policy
    0.22
     mode
    0.20
    Strategy
    0.20
    Enabled
    0.20
     Mode
    0.19
    -mode
    0.19
    -policy
    0.19
    Act Density 0.593%

    No Known Activations