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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or the word "the" in various contexts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichen
    -0.17
    ç¨
    -0.16
    ollar
    -0.14
    ر
    -0.14
    SUCCESS
    -0.14
    ä¹ĭ
    -0.14
     required
    -0.14
    eds
    -0.13
    cer
    -0.13
    ie
    -0.13
    POSITIVE LOGITS
    aad
    0.15
     âĹĦ
    0.15
    kus
    0.14
    oks
    0.14
    umpt
    0.14
    coverage
    0.14
     duty
    0.14
     Zum
    0.14
    [Math
    0.14
    /renderer
    0.13
    Act Density 0.049%

    No Known Activations