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

    Neuronpedia

    INDEX
    Explanations

    terms related to problems, issues, or controversies

    oai_token-act-pair · gpt-3.5-turbo

    complex words with multiple syllables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NCT
    -0.74
    \/\/
    -0.74
     Willow
    -0.66
     tidal
    -0.64
    ensional
    -0.64
    ¯
    -0.61
    ufact
    -0.60
     Constantine
    -0.58
    ovych
    -0.58
     Benz
    -0.58
    POSITIVE LOGITS
    rency
    0.94
    cled
    0.92
    cling
    0.77
    cius
    0.74
    ña
    0.73
    Browser
    0.71
    inence
    0.71
    brance
    0.70
     pestic
    0.70
    rences
    0.66
    Act Density 0.133%

    No Known Activations