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

    Neuronpedia

    INDEX
    Explanations

    references to the word "boost" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dezelve
    -0.59
     quæ
    -0.53
     zijne
    -0.48
     autorytatywna
    -0.46
     congi
    -0.46
     vrijwilli
    -0.45
    FormTagHelper
    -0.45
    räck
    -0.45
    styleType
    -0.45
     volontaire
    -0.45
    POSITIVE LOGITS
     boost
    1.06
     boosts
    0.93
    boost
    0.89
     boosted
    0.88
     boosting
    0.86
     Boost
    0.84
    Boost
    0.80
     BOOST
    0.75
     enhancements
    0.68
     enhance
    0.68
    Act Density 0.072%

    No Known Activations