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

    Neuronpedia

    INDEX
    Explanations

    references to specific articles and their related citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DDL
    -0.16
    utable
    -0.15
    868
    -0.15
     undert
    -0.15
    irsch
    -0.14
    ris
    -0.14
    695
    -0.14
    395
    -0.14
    uest
    -0.14
     Beg
    -0.14
    POSITIVE LOGITS
     horizon
    0.17
    ube
    0.16
    UBE
    0.16
    ucker
    0.16
    usk
    0.15
    ết
    0.15
    à¸IJาà¸Ļ
    0.15
     Tube
    0.14
    zin
    0.14
     Tubes
    0.14
    Act Density 0.066%

    No Known Activations