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

    Neuronpedia

    INDEX
    Explanations

    expressions of well-being or positive acknowledgment in a conversation

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

    bien or bem succeeded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DCS
    -0.40
     Seitz
    -0.40
    PullParser
    -0.39
    フォン
    -0.39
     YP
    -0.39
    チール
    -0.38
     Machado
    -0.38
     Ihre
    -0.37
     Palacios
    -0.37
     Mueller
    -0.37
    POSITIVE LOGITS
     bem
    1.65
    Bem
    1.41
     Bem
    1.32
     bien
    1.10
     BEM
    1.03
     BIEN
    1.00
    bem
    0.91
     Bien
    0.88
    Bien
    0.87
    Well
    0.85
    Act Density 0.002%

    No Known Activations