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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or places

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.75
     censored
    -0.68
     Xin
    -0.66
     Tibetan
    -0.61
     Korra
    -0.61
     heroin
    -0.61
     futures
    -0.60
     responsible
    -0.59
    BuyableInstoreAndOnline
    -0.59
    ENSE
    -0.59
    POSITIVE LOGITS
    izophren
    1.31
    izoph
    1.31
    utz
    1.24
    umann
    1.20
    uler
    1.17
    mitt
    1.14
    acht
    1.12
    mid
    1.12
    afer
    1.10
    ulz
    1.09
    Act Density 0.021%

    No Known Activations