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

    Neuronpedia

    INDEX
    Explanations

    technical information related to research procedures and compliance with regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    CONCLUS
    -0.54
    CppCodeGen
    -0.51
     Feier
    -0.50
    bParam
    -0.48
    glPushMatrix
    -0.46
     something
    -0.46
    ☉
    -0.45
     billion
    -0.45
     billions
    -0.44
     Braut
    -0.44
    POSITIVE LOGITS
     makro
    1.16
     stik
    1.14
     disagre
    1.14
     fup
    1.13
     effe
    1.12
     elek
    1.10
     excru
    1.10
     overla
    1.09
     aen
    1.09
     perfon
    1.09
    Act Density 0.285%

    No Known Activations