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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns, indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Possessive adjectives (your, my, our)

    np_acts-logits-general · gemini-2.0-flash

    personal possessions and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bourgoin
    -0.47
    ViewFeatures
    -0.47
    enschaft
    -0.45
     carattere
    -0.45
     egenskaper
    -0.44
     possano
    -0.44
    ėk
    -0.43
    AddTagHelper
    -0.43
     AssemblyTitle
    -0.41
    WriteTagHelper
    -0.41
    POSITIVE LOGITS
    mybatisplus
    0.70
    MathML
    0.64
     numberWith
    0.62
    abestanden
    0.62
     choices
    0.62
    はじめに
    0.62
    0.61
     <>",
    0.60
     choice
    0.59
     المثال
    0.59
    Act Density 0.271%

    No Known Activations