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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a context or relationship involving advancements or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apult
    -0.15
    erez
    -0.15
    ulti
    -0.15
    ecess
    -0.15
    ildi
    -0.14
    .Slf
    -0.14
     cé
    -0.14
    hiro
    -0.14
    arend
    -0.13
    cepts
    -0.13
    POSITIVE LOGITS
    utow
    0.20
    alace
    0.15
     increasing
    0.14
    nest
    0.14
    orial
    0.14
    tm
    0.14
     clock
    0.14
     ná»ģn
    0.14
    Increasing
    0.14
     Emin
    0.14
    Act Density 0.056%

    No Known Activations