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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and code elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gzip
    -0.16
    reate
    -0.16
     Bray
    -0.15
    аÑĢÑı
    -0.15
    ollo
    -0.15
    astle
    -0.15
     Knight
    -0.14
    Knight
    -0.14
     u
    -0.14
    -u
    -0.14
    POSITIVE LOGITS
    PTS
    0.19
     lav
    0.18
    nal
    0.18
     PTS
    0.18
    lav
    0.18
     av
    0.17
    nero
    0.17
     showc
    0.17
    InParameter
    0.17
    avs
    0.16
    Act Density 0.022%

    No Known Activations