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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    824
    -0.15
     bore
    -0.15
    TextWriter
    -0.14
    959
    -0.14
     Fon
    -0.14
    558
    -0.14
     reli
    -0.13
    .bitmap
    -0.13
    master
    -0.13
    /wiki
    -0.13
    POSITIVE LOGITS
    ibel
    0.15
    los
    0.15
    ãĥ¼ãĥģ
    0.15
    asons
    0.15
     underlying
    0.15
    ë²Į
    0.14
    رÙĪب
    0.14
    oder
    0.14
    θÏħ
    0.14
    ials
    0.14
    Act Density 0.049%

    No Known Activations