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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles and sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.15
    695
    -0.15
    irsch
    -0.14
    DDL
    -0.14
     POW
    -0.14
     scratch
    -0.14
     Sad
    -0.14
     undert
    -0.14
    395
    -0.14
    868
    -0.14
    POSITIVE LOGITS
    ube
    0.17
    UBE
    0.17
     horizon
    0.16
    ết
    0.16
    zin
    0.16
    ucker
    0.15
    à¸IJาà¸Ļ
    0.15
     Barcode
    0.14
    usk
    0.14
    oint
    0.14
    Act Density 0.070%

    No Known Activations