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

    Neuronpedia

    INDEX
    Explanations

    references to gold and its various contexts or attributes

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

    "gold" or "golden"

    np_acts-logits-general · gemini-2.0-flash

    gold and Chinese phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pstmt
    -0.72
     TestBed
    -0.62
     Audiodateien
    -0.60
     ostavi
    -0.60
     Slaughter
    -0.60
     kệ
    -0.60
     compri
    -0.59
    TProtocol
    -0.58
     Mue
    -0.58
     Dishwasher
    -0.56
    POSITIVE LOGITS
     gold
    1.15
     GOLD
    1.12
     Gold
    1.08
    GOLD
    1.03
    Gold
    1.02
    golden
    1.02
     Golden
    1.01
     golden
    1.01
    gold
    0.99
    Golden
    0.96
    Act Density 0.133%

    No Known Activations