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

    Neuronpedia

    INDEX
    Explanations

    expressions of intention or future planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.90
     AssemblyCompany
    -0.81
    abetes
    -0.79
    NameInMap
    -0.70
    наче
    -0.70
     AssemblyCulture
    -0.69
    AndEndTag
    -0.68
    DeleteBehavior
    -0.66
     Biôgrafia
    -0.66
    IsMutable
    -0.65
    POSITIVE LOGITS
     to
    0.69
     wants
    0.49
    จะ
    0.48
    ที่จะ
    0.48
     abzu
    0.46
     να
    0.45
     want
    0.45
     vrea
    0.43
     smör
    0.42
     intends
    0.42
    Act Density 0.173%

    No Known Activations