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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-reflection and introspection

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

    have to understand/believe/realize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.41
     Wart
    -0.41
     ואת
    -0.33
    doc
    -0.31
    ようになる
    -0.30
    清
    -0.30
     Royal
    -0.29
    LEM
    -0.29
    OwnerId
    -0.29
     fra
    -0.29
    POSITIVE LOGITS
    AndEndTag
    0.71
     مشين
    0.68
     wireType
    0.60
     laſſen
    0.58
     AssemblyCulture
    0.57
     hinweg
    0.57
    ACHUSET
    0.56
     wiſſen
    0.56
     Verſ
    0.56
     beſch
    0.56
    Act Density 0.050%

    No Known Activations