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

    Neuronpedia

    INDEX
    Explanations

    references to Harvard University

    oai_token-act-pair · gpt-3.5-turbo

    references to Harvard University and its associated institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afort
    -0.68
    arding
    -0.67
    wagon
    -0.66
     recip
    -0.64
    arde
    -0.63
    alez
    -0.63
    phabet
    -0.63
    abiding
    -0.62
    aepernick
    -0.62
    finder
    -0.61
    POSITIVE LOGITS
     University
    1.43
     undergrad
    1.11
     professors
    1.10
     Graduate
    1.09
     Divinity
    1.09
     professor
    1.05
     Univ
    1.03
    University
    1.02
     Law
    1.00
     faculty
    0.99
    Act Density 0.075%

    No Known Activations