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

    Neuronpedia

    INDEX
    Explanations

    references to organizational or structural components within a codebase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ryn
    -0.17
    irut
    -0.16
    ahan
    -0.15
    .heroku
    -0.15
    owl
    -0.14
    itters
    -0.14
    amber
    -0.14
    .owl
    -0.14
    aan
    -0.14
    ifact
    -0.14
    POSITIVE LOGITS
    .uk
    0.18
    .scalablytyped
    0.17
    utan
    0.15
    BERS
    0.15
    į
    0.14
    _endian
    0.14
    heimer
    0.14
    times
    0.13
    startTime
    0.13
    .weixin
    0.13
    Act Density 0.025%

    No Known Activations