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

    Neuronpedia

    INDEX
    Explanations

    references to gold and its qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mListener
    -0.73
     compri
    -0.66
     Everybody
    -0.64
    "\"
    -0.64
    rég
    -0.63
     Sheets
    -0.63
    everybody
    -0.63
    клопе
    -0.63
     everybody
    -0.63
     somebody
    -0.62
    POSITIVE LOGITS
     Gold
    2.14
    Gold
    2.07
     gold
    2.06
     GOLD
    2.00
    gold
    1.91
    GOLD
    1.67
     Goldstein
    1.41
     gouden
    1.24
     Goldsmith
    1.23
    golden
    1.21
    Act Density 0.027%

    No Known Activations