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

    Neuronpedia

    INDEX
    Explanations

    question marks and other punctuation that indicates questions or conditional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illisecond
    -0.16
    rosso
    -0.16
    aps
    -0.16
     seedu
    -0.15
    ãĥ«ãĥĪ
    -0.15
    utdown
    -0.15
    ãģĵãģĿ
    -0.15
    ÃŃrk
    -0.14
    ãģ¿
    -0.14
    richt
    -0.14
    POSITIVE LOGITS
    rious
    0.17
    intptr
    0.14
    ï¸ı
    0.14
     Colin
    0.14
    php
    0.14
    ptrdiff
    0.14
    ively
    0.13
    repid
    0.13
    naires
    0.13
    ably
    0.13
    Act Density 0.035%

    No Known Activations