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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting related to lists or data entries

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     picioare
    -0.55
     dignité
    -0.54
     wikipagina
    -0.54
    AntiForgeryToken
    -0.54
    ơi
    -0.52
     pesante
    -0.51
     gouvern
    -0.50
    TextColor
    -0.49
     victoire
    -0.48
    geten
    -0.48
    POSITIVE LOGITS
     disambiguazione
    0.92
     InputDecoration
    0.83
    ReusableCell
    0.83
    Tembelea
    0.81
     ujednoznacz
    0.79
     gynhyrchwyd
    0.78
    WebVitals
    0.75
     utafitiHapana
    0.75
    UserScript
    0.72
    ItemBackground
    0.72
    Act Density 0.004%

    No Known Activations