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

    Neuronpedia

    INDEX
    Explanations

    academic references and grading metrics related to education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undergraduate
    -0.21
     undergrad
    -0.18
    大åѦ
    -0.18
     Univers
    -0.17
     UNIVERSITY
    -0.17
     professor
    -0.17
     university
    -0.17
     University
    -0.17
     professors
    -0.17
    大åѸ
    -0.17
    POSITIVE LOGITS
     High
    0.26
     high
    0.26
    HS
    0.24
    é«ĺä¸Ń
    0.23
     HS
    0.20
    High
    0.20
     boys
    0.19
     secondary
    0.19
    high
    0.19
     RHS
    0.19
    Act Density 0.373%

    No Known Activations