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

    Neuronpedia

    INDEX
    Explanations

    references to mailing lists and newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deck
    -0.17
    iegel
    -0.16
    atomy
    -0.16
    å¯Ł
    -0.15
     decks
    -0.15
    ning
    -0.15
    ses
    -0.14
     deck
    -0.14
    -0.14
     Person
    -0.14
    POSITIVE LOGITS
    rana
    0.17
    .sul
    0.15
    živ
    0.15
    sled
    0.14
    @student
    0.14
     ì¹ĺ
    0.14
    BIT
    0.14
    yonel
    0.14
     fur
    0.14
    _tracking
    0.14
    Act Density 0.031%

    No Known Activations