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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols used to structure statements and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arent
    -0.15
    pute
    -0.15
    haven
    -0.15
    iny
    -0.15
    wayne
    -0.14
    :numel
    -0.14
     Fleming
    -0.14
    AREN
    -0.14
    erne
    -0.14
     kami
    -0.14
    POSITIVE LOGITS
    ardu
    0.15
    enge
    0.15
     writable
    0.14
    AndView
    0.14
    даÑı
    0.14
    /Foundation
    0.14
    enger
    0.14
    datable
    0.14
    éru
    0.14
     Tu
    0.13
    Act Density 0.253%

    No Known Activations