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

    Neuronpedia

    INDEX
    Explanations

    references to Harvard and Stanford universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ape
    -0.16
    iw
    -0.16
    aleigh
    -0.15
    aeda
    -0.14
    azard
    -0.14
    +xml
    -0.14
    ala
    -0.14
    enha
    -0.14
    erton
    -0.13
    allah
    -0.13
    POSITIVE LOGITS
     University
    0.33
     UNIVERSITY
    0.26
    .edu
    0.26
    University
    0.26
    -educated
    0.24
    大åѦ
    0.22
    ëĮĢíķĻêµIJ
    0.22
     university
    0.21
     Ãľniversitesi
    0.21
    shire
    0.20
    Act Density 0.025%

    No Known Activations