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

    Neuronpedia

    INDEX
    Explanations

    terms related to a programming language, specifically SQL (Structured Query Language)

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'Q' in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.90
    fulness
    -0.84
     Lauder
    -0.78
    coni
    -0.70
    wagen
    -0.66
     Magicka
    -0.66
     Dortmund
    -0.65
    itored
    -0.64
     Nadu
    -0.64
     fullest
    -0.62
    POSITIVE LOGITS
    UE
    1.16
    ues
    0.98
    uably
    0.96
    WER
    0.91
    atar
    0.91
    atari
    0.90
    ued
    0.90
    addafi
    0.83
    naire
    0.83
    iao
    0.81
    Act Density 0.017%

    No Known Activations