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

    Neuronpedia

    INDEX
    Explanations

    references to discussions, comments, and recommendations in formal reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    &a
    -0.16
     scient
    -0.14
    .jav
    -0.14
     Say
    -0.13
     WHO
    -0.13
     cou
    -0.13
     lin
    -0.13
    imb
    -0.13
     mere
    -0.13
     Singapore
    -0.13
    POSITIVE LOGITS
    urahan
    0.17
    twig
    0.17
     Xuân
    0.16
    cene
    0.16
     Hüs
    0.15
    #aa
    0.14
    ören
    0.14
    HeaderCode
    0.14
    _WRAP
    0.14
    EncodingException
    0.14
    Act Density 0.011%

    No Known Activations