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

    Neuronpedia

    INDEX
    Explanations

    references to various types of scientists and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holders
    -0.16
    ỡ
    -0.15
    ents
    -0.15
    er
    -0.15
    RAY
    -0.15
    erez
    -0.15
    kommen
    -0.14
    ÑĸÑĤÑĮ
    -0.14
    anine
    -0.14
     بÙĨدÛĮ
    -0.14
    POSITIVE LOGITS
    ically
    0.22
    urally
    0.19
    /engine
    0.18
    ical
    0.17
    ICAL
    0.17
    ppo
    0.16
    unction
    0.16
    otle
    0.16
    isches
    0.15
    ropy
    0.15
    Act Density 0.137%

    No Known Activations