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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arians
    -0.17
    arta
    -0.16
    azzi
    -0.16
    inea
    -0.15
     quadr
    -0.14
    hod
    -0.14
    ocz
    -0.14
    865
    -0.14
    957
    -0.14
    zw
    -0.14
    POSITIVE LOGITS
    اÙĬد
    0.16
    aded
    0.16
    acct
    0.15
    agi
    0.15
    DataAdapter
    0.15
    brook
    0.14
    .SelectCommand
    0.14
    Uvs
    0.14
     Salvador
    0.14
    ipa
    0.13
    Act Density 0.008%

    No Known Activations