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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "gold" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¡ãĥ³ãĥĪ
    -0.16
    dre
    -0.15
    ÙĪدÛĮ
    -0.15
    dire
    -0.14
     guise
    -0.14
    ather
    -0.14
    apon
    -0.14
    /dialog
    -0.14
    dia
    -0.14
     Tome
    -0.14
    POSITIVE LOGITS
    smith
    0.27
    finger
    0.23
    fish
    0.22
    stein
    0.21
    reich
    0.20
    wyn
    0.19
    mine
    0.19
     rush
    0.19
     Nug
    0.19
    trap
    0.18
    Act Density 0.019%

    No Known Activations