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

    Neuronpedia

    INDEX
    Explanations

    mentions of academic degrees and educational qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    813
    -0.15
    ODB
    -0.14
     Bru
    -0.14
     Gol
    -0.14
    uran
    -0.13
    utable
    -0.13
     reh
    -0.13
    ç
    -0.13
     Dah
    -0.13
    auge
    -0.13
    POSITIVE LOGITS
     degree
    0.42
     degrees
    0.39
    degree
    0.35
     Degree
    0.33
    -degree
    0.32
    degrees
    0.32
    _degree
    0.31
    .degree
    0.30
     Degrees
    0.30
     bachelor
    0.29
    Act Density 0.371%

    No Known Activations