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

    Neuronpedia

    INDEX
    Explanations

    terms related to misinformation and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .nih
    -0.16
    odon
    -0.16
    lsi
    -0.15
    ranÃŃ
    -0.15
    ramework
    -0.15
    ìļ´ëį°
    -0.15
    /ns
    -0.14
    à¹īà¸Ńà¸Ļ
    -0.14
    AUSE
    -0.14
    æ¡ij
    -0.14
    POSITIVE LOGITS
    etin
    0.15
    quine
    0.15
    entication
    0.14
    unpack
    0.13
    busters
    0.13
    cient
    0.13
    baugh
    0.13
    uben
    0.13
    gow
    0.13
    orum
    0.13
    Act Density 0.271%

    No Known Activations