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

    Neuronpedia

    INDEX
    Explanations

    words related to specific names or terms ("Kwak", "Gwinnett", "Kawai", etc.)

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns or names, particularly those that start with "Kw," "Gw," and "Kaw."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ++++++++++++++++
    -0.79
    ional
    -0.73
    ãĥĩãĤ£
    -0.73
    cells
    -0.72
    ãĥ¼ãĥĨ
    -0.72
    IAL
    -0.71
    gered
    -0.68
    naissance
    -0.68
    gio
    -0.66
    âĸ¬âĸ¬
    -0.66
    POSITIVE LOGITS
     Kw
    1.05
    erk
    0.89
    atts
    0.88
    itzer
    0.84
    arna
    0.79
    orea
    0.78
    edge
    0.78
    atsu
    0.78
    arp
    0.78
    urst
    0.78
    Act Density 0.006%

    No Known Activations