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

    Neuronpedia

    INDEX
    Explanations

    terms related to advancements in neural network architectures and dialogue systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sov
    -0.15
     Tub
    -0.15
     tub
    -0.15
    Coder
    -0.14
    aiser
    -0.14
    iefs
    -0.14
     Clarke
    -0.14
    defgroup
    -0.14
    laus
    -0.14
    ány
    -0.14
    POSITIVE LOGITS
    bite
    0.16
    etine
    0.15
    paque
    0.15
    aba
    0.15
    itta
    0.14
    /cat
    0.14
    orse
    0.14
    phas
    0.14
     automát
    0.14
    Overlap
    0.14
    Act Density 0.033%

    No Known Activations