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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks or symbols indicating emphasis or significant changes in tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meisten
    -0.16
    och
    -0.15
    /or
    -0.13
    áºŃu
    -0.13
    um
    -0.13
     Memorial
    -0.13
    esi
    -0.13
    lett
    -0.13
    ations
    -0.12
    abel
    -0.12
    POSITIVE LOGITS
    sak
    0.18
    å£°éŁ³
    0.17
    \/\/
    0.16
    \<^
    0.16
    s
    0.16
    nbsp
    0.16
    ydı
    0.15
    ska
    0.15
    ftware
    0.15
    sian
    0.15
    Act Density 0.257%

    No Known Activations