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

    Neuronpedia

    INDEX
    Explanations

    references to academic institutions, specifically universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hör
    -0.65
     chilen
    -0.62
    peč
    -0.62
     PDT
    -0.61
    cod
    -0.60
     krak
    -0.60
     Parigi
    -0.59
     Vierge
    -0.59
     Ketch
    -0.59
    }{||
    -0.58
    POSITIVE LOGITS
     university
    1.77
     University
    1.74
    university
    1.60
     universities
    1.57
    University
    1.48
     Universities
    1.40
     universitarios
    1.38
     UNIVERSITY
    1.32
    université
    1.30
    versities
    1.26
    Act Density 0.038%

    No Known Activations