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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and textual formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elib
    -0.15
    ãĥĨãĥ«
    -0.15
    å¤
    -0.15
    hong
    -0.14
    нки
    -0.14
    edl
    -0.14
    æķı
    -0.14
    ference
    -0.13
    imus
    -0.13
    æĸ¹
    -0.13
    POSITIVE LOGITS
     Barr
    0.15
    779
    0.15
    otta
    0.15
    wort
    0.15
    673
    0.14
     Chandler
    0.14
    azzi
    0.14
    angan
    0.13
    ans
    0.13
    724
    0.13
    Act Density 0.091%

    No Known Activations