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

    Neuronpedia

    INDEX
    Explanations

    terms related to comment moderation and user privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inke
    -0.17
    otta
    -0.15
    434
    -0.15
    åĨł
    -0.14
     Bounds
    -0.14
    ç±į
    -0.14
    coverage
    -0.14
     ÐľÐ¾Ð¶Ð½Ð¾
    -0.14
    693
    -0.14
    al
    -0.13
    POSITIVE LOGITS
    ADVERTISEMENT
    0.17
     manual
    0.15
    ODY
    0.15
     Palestine
    0.15
     rencont
    0.14
    buat
    0.14
     Manual
    0.14
    manual
    0.14
    ãĤ¤ãĤ¹
    0.14
    AllowAnonymous
    0.14
    Act Density 0.073%

    No Known Activations