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

    Neuronpedia

    INDEX
    Explanations

    names of universities

    oai_token-act-pair · gpt-3.5-turbo

    references to universities and academic institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wagon
    -0.85
     specials
    -0.66
     anthem
    -0.65
     Militia
    -0.65
     plun
    -0.64
     filler
    -0.64
     bumper
    -0.64
     Tornado
    -0.63
     countdown
    -0.62
     absentee
    -0.61
    POSITIVE LOGITS
    University
    1.33
     University
    1.21
     universities
    1.16
     Institute
    1.13
     Faculty
    1.07
     Univers
    1.07
     NYU
    0.98
     university
    0.97
     Universities
    0.96
    Research
    0.96
    Act Density 0.228%

    No Known Activations