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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting symbols in unstructured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \<^
    -1.29
    URLException
    -1.29
    NUMX
    -1.28
    >\<^
    -1.21
    setVerticalGroup
    -1.20
     \\
    -1.18
    )";
    -1.16
    .")
    -1.14
    &
    -1.14
    ".
    -1.12
    POSITIVE LOGITS
    <eos>
    1.35
    ...
    1.12
    …
    1.05
    ↵
    1.04
     ...
    1.01
    ↵↵
    0.99
     |
    0.95
     -
    0.91
    .
    0.89
    ..
    0.87
    Act Density 0.300%

    No Known Activations