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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain keywords related to programming and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     refl
    -0.16
    anzi
    -0.16
    arin
    -0.15
    morgan
    -0.15
     ÏĨοÏģ
    -0.15
     Hunger
    -0.14
     Kak
    -0.14
     å¼
    -0.14
    reib
    -0.14
    εί
    -0.14
    POSITIVE LOGITS
    ogi
    0.16
    инÑĥв
    0.15
    ãĥ³ãĥIJ
    0.15
    ozo
    0.15
    olid
    0.14
    spiel
    0.14
    umph
    0.14
    кÑĤа
    0.14
     bis
    0.14
    brook
    0.14
    Act Density 0.001%

    No Known Activations