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

    Neuronpedia

    INDEX
    Explanations

    elements of personal identity and self-reflection

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

    phrases describing what shapes or defines a person's identity and character.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.38
    참고
    -0.35
    最快更新
    -0.32
     Reverso
    -0.32
    ensement
    -0.30
     solches
    -0.29
     atras
    -0.28
    RenderAtEndOf
    -0.28
    rys
    -0.28
    ByUser
    -0.28
    POSITIVE LOGITS
     who
    2.58
    Who
    2.23
     Who
    2.20
    who
    2.08
     quién
    2.03
     hvem
    1.85
     quien
    1.83
     siapa
    1.78
    是谁
    1.67
    谁
    1.64
    Act Density 0.326%

    No Known Activations