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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "new."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    played
    -0.18
    cern
    -0.16
    csr
    -0.15
    ÑĢаж
    -0.15
    SCRIPTION
    -0.15
    ie
    -0.15
    .scrollTo
    -0.15
    ilen
    -0.14
    .getBlock
    -0.14
    StateChanged
    -0.14
    POSITIVE LOGITS
     recruits
    0.17
    TON
    0.15
    emente
    0.15
    ubre
    0.15
    illis
    0.15
    ests
    0.15
    ton
    0.15
    icamente
    0.14
    iou
    0.14
     çıkan
    0.14
    Act Density 0.060%

    No Known Activations