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

    Neuronpedia

    INDEX
    Explanations

    terms related to improvement or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ne
    -0.75
     ne
    -0.65
    Ne
    -0.62
    a
    -0.59
    н
    -0.58
     Ne
    -0.57
     d
    -0.57
    jod
    -0.56
    o
    -0.56
    fox
    -0.56
    POSITIVE LOGITS
    hancing
    1.44
     enhancements
    1.23
     BOOST
    1.21
     enhancement
    1.17
     boost
    1.16
     boosts
    1.14
    BOOST
    1.13
     Boost
    1.12
    boost
    1.12
     enhance
    1.08
    Act Density 0.205%

    No Known Activations