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

    Neuronpedia

    INDEX
    Explanations

    references to scientific journals and papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.47
    󠁢
    -0.42
     kant
    -0.42
    袍
    -0.42
     Inter
    -0.41
    ուն
    -0.40
    ਹਾ
    -0.40
    chot
    -0.40
    Inter
    -0.39
    ↵↵
    -0.39
    POSITIVE LOGITS
     дописавши
    1.09
     للاسماء
    1.00
     MonoBehaviour
    0.97
     kaarangay
    0.96
     EconPapers
    0.89
    verwijspagina
    0.89
     propOrder
    0.88
    Datuak
    0.86
     autorytatywna
    0.80
     lenker
    0.80
    Act Density 0.685%

    No Known Activations