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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "l" followed by a number in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or letter in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.86
    rolet
    -0.74
    ħĭ
    -0.70
    ãĥ¼ãĤ¯
    -0.68
    ãĤ®
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    ramid
    -0.66
    ij士
    -0.66
    ItemTracker
    -0.65
    uyomi
    -0.65
    POSITIVE LOGITS
    adders
    1.19
    ibr
    1.14
    ips
    1.05
    ipp
    1.04
    ibrarian
    1.04
    asso
    1.03
    idd
    0.99
    yrics
    0.99
    isted
    0.98
    ugs
    0.98
    Act Density 0.016%

    No Known Activations