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

    Neuronpedia

    INDEX
    Explanations

    expressions related to research findings and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.62
     متعلقه
    -0.60
    ValueStyle
    -0.60
    WriteTagHelper
    -0.58
    expandindo
    -0.58
    setVerticalGroup
    -0.58
     дописавши
    -0.57
     '\\;'
    -0.57
    Tembelea
    -0.56
    المكان
    -0.55
    POSITIVE LOGITS
     tampak
    0.34
     aneh
    0.32
     odd
    0.32
    gonic
    0.30
    kémon
    0.30
     auff
    0.30
     tapasztal
    0.29
    แพ
    0.29
     sekali
    0.29
    奇怪
    0.29
    Act Density 1.261%

    No Known Activations