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

    Neuronpedia

    INDEX
    Explanations

    mentions of university students and student-related activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    aurus
    -1.16
    ilver
    -0.84
    mith
    -0.84
    ensitive
    -0.84
    ecause
    -0.83
    chool
    -0.82
    uits
    -0.82
    ophical
    -0.81
    pots
    -0.80
    erence
    -0.79
    POSITIVE LOGITS
    hood
    0.80
     loan
    0.80
     uprising
    0.78
     visa
    0.77
    76561
    0.77
    holder
    0.75
     Loan
    0.75
     affairs
    0.74
     council
    0.70
     visas
    0.69
    Act Density 0.176%

    No Known Activations