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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✨:
    -0.62
    qrstuvwxyz
    -0.54
    featureID
    -0.52
    testng
    -0.52
    AndEndTag
    -0.50
    ibatis
    -0.48
    ]='\
    -0.48
    XtraReports
    -0.48
    gespräch
    -0.47
    igua
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.74
     invokingState
    0.69
    AntiForgeryToken
    0.67
    __*/
    0.65
     Skor
    0.55
     iParam
    0.51
    istoitu
    0.51
    testens
    0.50
     ویکی‌پدیا
    0.50
    </thead>
    0.48
    Act Density 0.175%

    No Known Activations