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

    Neuronpedia

    INDEX
    Explanations

    occurrences of common words and phrases that suggest narrative structure or legal/court-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Burl
    -0.16
    azu
    -0.15
    eland
    -0.15
    üven
    -0.15
    ala
    -0.15
    _si
    -0.15
    izu
    -0.14
    zi
    -0.14
    /register
    -0.14
     cap
    -0.14
    POSITIVE LOGITS
    agers
    0.17
    anki
    0.16
    éĥİ
    0.16
    864
    0.16
    tics
    0.15
    uela
    0.15
    xit
    0.14
    illes
    0.14
    кÑĥÑģ
    0.14
     ÙĨسبة
    0.14
    Act Density 0.021%

    No Known Activations