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

    Neuronpedia

    INDEX
    Explanations

    the beginning and end markers of documents or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.65
    lark
    -0.65
    parsedMessage
    -0.62
    queryInterface
    -0.61
    //
    -0.60
    tea
    -0.58
    Kjelder
    -0.56
    elope
    -0.56
     StatefulWidget
    -0.56
    €”
    -0.56
    POSITIVE LOGITS
    ;#
    0.97
    ########.
    0.80
     referrerpolicy
    0.66
     تضيفلها
    0.65
    &
    0.64
    bukkit
    0.63
    &#
    0.62
    ;&
    0.61
    -&
    0.59
     pamamagitan
    0.57
    Act Density 0.060%

    No Known Activations