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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate permission or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -1.35
     AssemblyCompany
    -1.19
     &___
    -1.11
     كومونز
    -1.08
    TypedDataSet
    -1.04
     jLabel
    -1.02
    KURZBESCHREIBUNG
    -1.01
     jScrollPane
    -1.00
     disambiguazione
    -0.99
    Зноскі
    -0.98
    POSITIVE LOGITS
     to
    1.76
     able
    0.71
    to
    0.67
     want
    0.65
     need
    0.65
     attempt
    0.62
     чтобы
    0.60
    ToUpdate
    0.55
     să
    0.54
    ToAdd
    0.52
    Act Density 0.702%

    No Known Activations