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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and keywords in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orn
    -0.15
    ust
    -0.14
    iske
    -0.13
    emer
    -0.13
     stalo
    -0.13
    iddle
    -0.13
    omen
    -0.13
    quine
    -0.13
    aise
    -0.12
    ran
    -0.12
    POSITIVE LOGITS
    AMP
    0.15
    åIJ¾
    0.15
    emiz
    0.14
    Impl
    0.14
     trimmed
    0.14
    108
    0.14
    itoris
    0.14
    rych
    0.14
    woff
    0.14
    _UNS
    0.14
    Act Density 0.058%

    No Known Activations