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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.23
    ↵
    -0.21
    ’.↵↵
    -0.14
    aseline
    -0.13
    ;.
    -0.13
    ’↵↵
    -0.13
    -deals
    -0.12
    '.↵↵
    -0.12
    obili
    -0.12
    responseData
    -0.12
    POSITIVE LOGITS
     ![
    0.29
    ![
    0.26
    ---↵
    0.24
    <img
    0.23
    ----↵
    0.22
    ---↵↵
    0.22
    ___↵↵
    0.22
     **
    0.22
    ***↵
    0.21
    <quote
    0.21
    Act Density 0.812%

    No Known Activations