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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in the format "mid-YYYY."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "mid" followed by a numeric range or descriptor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.84
     supervised
    -0.63
    士
    -0.62
     badges
    -0.62
     Fields
    -0.61
    éĹĺ
    -0.60
     Benef
    -0.60
     Bett
    -0.60
    naires
    -0.60
     disabilities
    -0.60
    POSITIVE LOGITS
    terms
    1.14
    section
    1.06
    season
    1.06
    -'
    1.04
    century
    1.03
    iors
    1.02
    west
    1.01
    sections
    1.00
    western
    0.96
    wives
    0.96
    Act Density 0.017%

    No Known Activations