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

    Neuronpedia

    INDEX
    Explanations

    references to medical criteria and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -1.39
    MLLoader
    -1.29
     queſta
    -1.27
    ValueStyle
    -1.23
    <unused52>
    -1.22
    parsedMessage
    -1.22
    <unused68>
    -1.21
    <unused79>
    -1.21
    <unused28>
    -1.21
    <unused16>
    -1.21
    POSITIVE LOGITS
    <unused63>
    0.17
    <unused61>
    0.15
    <eos>
    0.13
    <unused62>
    0.12
    <unused60>
    0.12
    ‌
    0.09
    .,
    0.06
     asequ
    0.06
     (!
    0.06
    ↵↵↵↵↵
    0.05
    Act Density 1.514%

    No Known Activations