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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of "the" and other high-frequency function words in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    transQ
    -0.74
    WindowConstants
    -0.65
     <<<<<<<<<<<<<<
    -0.61
     estekak
    -0.60
    AnimationsModule
    -0.60
    protoimpl
    -0.59
    GOTREF
    -0.58
    thâu
    -0.57
     NLA
    -0.57
     CommonModule
    -0.57
    POSITIVE LOGITS
     način
    0.51
     the
    0.50
     Gestión
    0.47
     efisien
    0.45
     vklju
    0.44
     recub
    0.43
     Fotografía
    0.43
     būti
    0.42
     Turquía
    0.42
     dekoratif
    0.42
    Act Density 1.243%

    No Known Activations