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

    Neuronpedia

    INDEX
    Explanations

    references to increasing or enhancing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Drey
    -0.85
    Nam
    -0.67
    complexContent
    -0.63
    WSER
    -0.62
    TemporalType
    -0.62
    BeforeMethod
    -0.62
    utilisons
    -0.61
    SPATH
    -0.60
    hund
    -0.60
    riwal
    -0.60
    POSITIVE LOGITS
     boost
    2.74
     Boost
    2.74
    boost
    2.65
    Boost
    2.63
     BOOST
    2.58
     boosts
    2.35
     boosting
    2.31
    BOOST
    2.28
     boosted
    2.16
     boosters
    1.95
    Act Density 0.063%

    No Known Activations