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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting elements often associated with text structure or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _Tis
    -0.07
    elage
    -0.07
    ynos
    -0.07
    oland
    -0.07
    oli
    -0.07
    ÏĦολ
    -0.07
    /Dk
    -0.07
    вÑĸлÑĮ
    -0.07
     pis
    -0.07
    .Suppress
    -0.07
    POSITIVE LOGITS
    forge
    0.07
     Bowman
    0.06
    farm
    0.06
    zer
    0.06
    лад
    0.05
     ê¼
    0.05
    zent
    0.05
     Alleg
    0.05
    isure
    0.05
    izen
    0.05
    Act Density 0.002%

    No Known Activations