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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ıs
    -0.14
    پس
    -0.14
     –↵↵
    -0.14
    zel
    -0.14
    éis
    -0.14
    reds
    -0.13
    wat
    -0.13
    iddles
    -0.13
    \system
    -0.13
    stup
    -0.13
    POSITIVE LOGITS
     And
    0.17
    And
    0.17
    że
    0.17
     hen
    0.16
    licken
    0.16
    æĹ
    0.14
    %E
    0.14
     nieu
    0.14
    jan
    0.14
     pixmap
    0.14
    Act Density 0.123%

    No Known Activations