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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that express conclusion or summary in dialogue

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

    said somebody

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astéroïdes
    -0.64
    -0.52
     propOrder
    -0.50
    Chham
    -0.48
    hyrchwyd
    -0.47
    LabelTagHelper
    -0.46
    是中国
    -0.44
    الإنجليزية
    -0.44
    migrationBuilder
    -0.44
    お楽しみに
    -0.43
    POSITIVE LOGITS
    ########.
    0.64
    Anybody
    0.40
     yeah
    0.38
     somebody
    0.38
     مشارکت‌کنندگان
    0.38
    fortawesome
    0.38
    ⓧ
    0.37
     anybody
    0.36
     Yeah
    0.35
     derro
    0.35
    Act Density 0.008%

    No Known Activations