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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coni
    -0.17
     جاÙĨ
    -0.15
    ķĮ
    -0.14
    ä¸Ī
    -0.14
    zan
    -0.14
    _PI
    -0.14
     Dual
    -0.14
     Pell
    -0.13
    otti
    -0.13
    OwnProperty
    -0.13
    POSITIVE LOGITS
    eten
    0.15
    299
    0.15
    523
    0.15
    298
    0.15
    rics
    0.14
     vintage
    0.14
     anz
    0.14
    797
    0.14
    ETCH
    0.13
    317
    0.13
    Act Density 0.007%

    No Known Activations