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

    Neuronpedia

    INDEX
    Explanations

    specific terms relating to conditional statements and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -1.33
     &___
    -1.09
    TypedDataSet
    -1.05
     /\.(
    -1.04
     AssemblyCompany
    -1.02
    GEBURTSDATUM
    -0.99
    Bioaccumulative
    -0.98
     lenker
    -0.98
    KURZBESCHREIBUNG
    -0.96
     "..\..\..\
    -0.96
    POSITIVE LOGITS
     to
    1.71
     want
    0.78
     able
    0.75
     need
    0.69
     attempt
    0.66
    to
    0.64
     чтобы
    0.61
     trebui
    0.60
     Want
    0.59
    ToUpdate
    0.57
    Act Density 0.704%

    No Known Activations