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

    Neuronpedia

    INDEX
    Explanations

    references to programming libraries and frameworks in the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.15
    stÃŃ
    -0.15
    ãĤ¸ãĤ§
    -0.15
    ALLERY
    -0.15
    äºĭæ¥Ń
    -0.14
     ci
    -0.14
     chung
    -0.14
    ngör
    -0.14
    뢰
    -0.14
    ittal
    -0.13
    POSITIVE LOGITS
     laps
    0.17
    pyx
    0.16
    portion
    0.15
    assa
    0.15
    apa
    0.14
    AGMA
    0.14
    iki
    0.14
    chest
    0.14
    .glide
    0.14
    uns
    0.14
    Act Density 0.005%

    No Known Activations