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

    Neuronpedia

    INDEX
    Explanations

    references to messages and event types in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.15
    emer
    -0.15
    _and
    -0.14
    same
    -0.14
    orne
    -0.14
     sque
    -0.14
    list
    -0.13
    rej
    -0.13
    ing
    -0.13
    herits
    -0.13
    POSITIVE LOGITS
    core
    0.18
    ::
    0.18
    -specific
    0.17
    _reserved
    0.16
     )↵↵↵↵↵↵↵↵
    0.16
    -INF
    0.16
    ::$
    0.16
    -Compatible
    0.16
    emento
    0.15
    ::*
    0.15
    Act Density 0.223%

    No Known Activations