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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in the text, especially commas and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    étoit
    -0.56
    SaveChanges
    -0.53
     Codable
    -0.53
     chaude
    -0.50
     costumbre
    -0.50
    Referencies
    -0.49
     poignée
    -0.49
     wiedzy
    -0.48
     őket
    -0.48
     skydd
    -0.48
    POSITIVE LOGITS
     Unitarian
    0.53
    1
    0.53
    GEBURTSDATUM
    0.51
     ویکی‌پدی
    0.50
    First
    0.49
     Firstly
    0.49
     First
    0.48
     firstname
    0.48
    getFirst
    0.47
    FIRST
    0.47
    Act Density 0.827%

    No Known Activations