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

    Neuronpedia

    INDEX
    Explanations

    terms related to inner qualities and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rol
    -0.16
    illo
    -0.15
    uli
    -0.15
     Fried
    -0.15
    ibi
    -0.14
    and
    -0.14
    acher
    -0.14
    asin
    -0.14
     trade
    -0.14
    otron
    -0.14
    POSITIVE LOGITS
    cco
    0.16
    eworthy
    0.15
    غÙĨ
    0.15
    ymous
    0.15
    uen
    0.15
    onne
    0.15
    Ïİ
    0.14
     Sesso
    0.14
    outu
    0.14
     Bernardino
    0.14
    Act Density 0.206%

    No Known Activations