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

    Neuronpedia

    INDEX
    Explanations

    references to the "nature" of different aspects or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss the nature of various subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kingdoms
    -0.60
    enegger
    -0.59
    ansson
    -0.58
    culosis
    -0.57
    alus
    -0.57
    inka
    -0.56
    olkien
    -0.56
    OTA
    -0.53
    igslist
    -0.53
     Wonderland
    -0.52
    POSITIVE LOGITS
     of
    1.19
     thereof
    1.08
    of
    1.00
    fulness
    0.91
     OF
    0.88
    iest
    0.86
    Of
    0.83
    liest
    0.83
     Of
    0.79
    lessness
    0.74
    Act Density 0.239%

    No Known Activations