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

    Neuronpedia

    INDEX
    Explanations

    structured elements or brackets in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.16
    STATE
    -0.16
    iban
    -0.15
    olia
    -0.15
    reon
    -0.15
    ÐIJÑĢÑħÑĸвовано
    -0.15
    eward
    -0.14
    ::__
    -0.14
    iki
    -0.14
    orre
    -0.14
    POSITIVE LOGITS
    gnore
    0.18
    drop
    0.18
    spo
    0.16
    ads
    0.16
    fab
    0.15
    丸
    0.15
    ais
    0.15
    aha
    0.14
    Trigger
    0.14
    .idea
    0.14
    Act Density 0.144%

    No Known Activations