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

    Neuronpedia

    INDEX
    Explanations

    references to titles or title sequences in various contexts

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

    title word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.48
     createState
    -0.44
    elemField
    -0.41
     founder
    -0.40
    BagConstraints
    -0.40
     Founder
    -0.40
     cout
    -0.40
    Founder
    -0.39
     Kit
    -0.38
     seaborn
    -0.38
    POSITIVE LOGITS
     judul
    0.76
     titles
    0.67
     tytu
    0.66
    RenderAtEndOf
    0.65
    标题
    0.64
     titolo
    0.63
     title
    0.60
    タイトル
    0.59
     Titles
    0.59
     título
    0.59
    Act Density 0.161%

    No Known Activations