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

    Neuronpedia

    INDEX
    Explanations

    names containing the letter "U"

    oai_token-act-pair · gpt-3.5-turbo

    references to universities, particularly those denoted by the letter "U" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Noir
    -0.78
     CPC
    -0.71
     CDs
    -0.66
     hust
    -0.66
     jammed
    -0.63
     Moz
    -0.63
     Preferred
    -0.62
     jams
    -0.62
     ashore
    -0.61
     Siberia
    -0.60
    POSITIVE LOGITS
    prising
    1.29
    nexpected
    1.13
    seless
    1.11
    lyss
    1.10
    gly
    1.04
    NA
    1.00
    topia
    0.98
    pperc
    0.97
    PDATED
    0.96
    CLA
    0.95
    Act Density 0.057%

    No Known Activations