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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and connective words that structure the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AREST
    -0.15
    aat
    -0.14
    \TestCase
    -0.14
    igy
    -0.14
     Dwight
    -0.14
    æĴ®
    -0.14
    æ±Ĺ
    -0.14
    WidgetItem
    -0.14
    меÑĩ
    -0.14
     sty
    -0.14
    POSITIVE LOGITS
    kup
    0.17
    addComponent
    0.15
     mir
    0.15
     mate
    0.14
     Wis
    0.14
    848
    0.14
    iris
    0.14
    ÑĥÑĤÑĮ
    0.14
    atten
    0.14
     outside
    0.14
    Act Density 0.000%

    No Known Activations