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

    Neuronpedia

    INDEX
    Explanations

    references to temporal markers or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    time expressions involving "after" and time periods like years, months, or hours.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    </thead>
    -0.56
    Chham
    -0.56
    autant
    -0.55
    upassen
    -0.52
     Motta
    -0.51
    Enllaces
    -0.50
    lining
    -0.49
    chtenstein
    -0.48
    nics
    -0.48
     Alternatives
    -0.48
    POSITIVE LOGITS
     sumpay
    0.57
    脚注の使い方
    0.56
     élo
    0.54
     geleden
    0.54
     ago
    0.53
    GEBURTSDATUM
    0.53
    ウンテン
    0.52
    +)$
    0.52
    principalTable
    0.50
    出版年
    0.49
    Act Density 0.294%

    No Known Activations