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

    Neuronpedia

    INDEX
    Explanations

    references to specific indices and the word "deck."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hasattr
    -0.56
     sae
    -0.56
     Paulina
    -0.55
     Machado
    -0.54
     Mongo
    -0.54
     yp
    -0.53
    OWE
    -0.53
     Cowper
    -0.53
     SAE
    -0.53
     Primera
    -0.52
    POSITIVE LOGITS
     deck
    0.90
     DECK
    0.85
     Deck
    0.83
    Viitteet
    0.79
    AddTagHelper
    0.79
    SourceChecksum
    0.77
    Deck
    0.75
     decks
    0.73
    WaitGroup
    0.73
     Decks
    0.73
    Act Density 0.080%

    No Known Activations