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

    Neuronpedia

    INDEX
    Explanations

    significant markers or identifiers in a text, such as names, key terms, or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     excer
    -0.15
    çĴĥ
    -0.15
     rodin
    -0.14
    YE
    -0.14
    udeau
    -0.14
     meisjes
    -0.14
    ourke
    -0.14
    thood
    -0.13
    ãĥ¼ãĥī
    -0.13
     sight
    -0.13
    POSITIVE LOGITS
    lig
    0.17
     Riders
    0.15
    .tf
    0.14
     Stevens
    0.14
    IENTATION
    0.14
     Couch
    0.14
    erca
    0.14
    ething
    0.14
    Ļ
    0.14
    ichen
    0.14
    Act Density 0.001%

    No Known Activations