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

    Neuronpedia

    INDEX
    Explanations

    structured data such as HTML or XML elements and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.55
     Monfieur
    -0.52
     myſelf
    -0.50
     purpoſe
    -0.48
     Theſe
    -0.46
     Majefty
    -0.46
     Jefus
    -0.46
     ſeveral
    -0.45
     themſelves
    -0.45
     himſelf
    -0.45
    POSITIVE LOGITS
    <bos>
    0.90
    ’
    0.34
    <eos>
    0.34
    MathML
    0.32
    enumi
    0.31
    </b>
    0.30
    </i>
    0.29
    ё
    0.28
    '
    0.28
    ­
    0.28
    Act Density 38.384%

    No Known Activations