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

    Neuronpedia

    INDEX
    Explanations

    instances of XML attributes in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yla
    -0.17
    ewitness
    -0.15
    agues
    -0.15
    ucid
    -0.14
    ayah
    -0.14
    hou
    -0.14
    éħ
    -0.14
    ÙĪÛĮÙĨت
    -0.13
    istra
    -0.13
     Pierce
    -0.13
    POSITIVE LOGITS
    redi
    0.18
    ĽĦ
    0.15
     Strand
    0.14
    .win
    0.14
    urgeon
    0.13
    hra
    0.13
    ÑĢÑĥн
    0.13
    αιν
    0.13
    LS
    0.13
    UCT
    0.13
    Act Density 0.007%

    No Known Activations