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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming and computer science libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Scaler
    -0.16
    ares
    -0.16
    ventional
    -0.15
    ven
    -0.14
     Aval
    -0.14
    erver
    -0.14
    364
    -0.14
     paints
    -0.14
    makt
    -0.13
    387
    -0.13
    POSITIVE LOGITS
     BOOST
    0.35
     boost
    0.33
     Boost
    0.32
    <boost
    0.30
    BOOST
    0.30
    boost
    0.28
     spirit
    0.27
    Boost
    0.26
     Spirit
    0.25
    .boost
    0.25
    Act Density 0.002%

    No Known Activations