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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presentation of results, lemmas, and theorems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.66
    KEYCODE
    -0.55
    InputBorder
    -0.55
    irmish
    -0.55
     препратки
    -0.55
    sizeCache
    -0.53
    السكان
    -0.52
     дописавши
    -0.52
     Biôgrafia
    -0.52
    клопе
    -0.51
    POSITIVE LOGITS
     haka
    0.55
     alphabetically
    0.54
    List
    0.54
     Libri
    0.52
    below
    0.52
     Jove
    0.52
     bellow
    0.51
     below
    0.50
     Tuc
    0.50
    下面
    0.50
    Act Density 0.019%

    No Known Activations