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

    Neuronpedia

    INDEX
    Explanations

    references to blog posts, papers, articles, and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayar
    -0.14
     aus
    -0.14
    egas
    -0.14
    ifton
    -0.14
    imate
    -0.13
    미
    -0.13
     Ner
    -0.13
    ardon
    -0.13
    unks
    -0.13
     rele
    -0.13
    POSITIVE LOGITS
    =-=-=-=-
    0.15
     stim
    0.15
    .UnitTesting
    0.14
    åĩĿ
    0.14
    .qual
    0.14
    ÙĨÛĮÙĨ
    0.14
    Ế
    0.13
     INTERRUPTION
    0.13
     ÙĪÙħا
    0.13
    /MPL
    0.13
    Act Density 0.070%

    No Known Activations