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

    Neuronpedia

    INDEX
    Explanations

    references to various types of reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.17
    aida
    -0.16
    Reporting
    -0.15
    ÐĴÑĤ
    -0.15
    anou
    -0.14
    ITY
    -0.14
    785
    -0.14
    estar
    -0.14
    ìĹĦ
    -0.14
    itsu
    -0.13
    POSITIVE LOGITS
     card
    0.32
    edly
    0.28
    orial
    0.27
     cards
    0.26
    able
    0.25
    ings
    0.25
     Cards
    0.23
    card
    0.23
    (card
    0.22
    -card
    0.22
    Act Density 0.033%

    No Known Activations