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

    Neuronpedia

    INDEX
    Explanations

    terms related to favorable outcomes and support in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordinaire
    -0.57
     Deane
    -0.54
    Qualifier
    -0.54
     mission
    -0.54
     Bourne
    -0.53
    <thead>
    -0.53
     ویکی‌آمباردا
    -0.51
     Pura
    -0.51
    sonder
    -0.50
     виправивши
    -0.49
    POSITIVE LOGITS
     favour
    1.36
     favoring
    1.30
     favor
    1.29
     Favor
    1.28
    Favor
    1.21
     Fav
    1.20
    favor
    1.18
    Fav
    1.13
     favourable
    1.11
     favors
    1.11
    Act Density 0.339%

    No Known Activations