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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols representing non-Latin scripts or languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹Ħà¸ĭ
    -0.15
    394
    -0.15
    tram
    -0.15
    782
    -0.14
    orge
    -0.14
    elsey
    -0.14
    aroo
    -0.14
    502
    -0.14
    ır
    -0.14
    ØŃÙħ
    -0.13
    POSITIVE LOGITS
    eri
    0.16
    olib
    0.15
    rij
    0.15
     resett
    0.15
     Tie
    0.15
    ±
    0.15
    .BorderFactory
    0.14
     Carpenter
    0.14
    ummer
    0.14
    mun
    0.14
    Act Density 0.008%

    No Known Activations