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

    Neuronpedia

    INDEX
    Explanations

    references to the United States

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "U.S." or references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Noir
    -0.76
     bars
    -0.72
     juggling
    -0.69
     courtesy
    -0.63
     Emin
    -0.60
     Dj
    -0.59
     Duty
    -0.58
     esc
    -0.58
     stiffness
    -0.58
     sentences
    -0.58
    POSITIVE LOGITS
    nexpected
    1.22
    prising
    1.18
    gly
    1.14
    mpire
    1.06
    PDATED
    1.05
    seless
    1.03
    lyss
    1.03
    LT
    1.00
    NA
    0.99
    psc
    0.96
    Act Density 0.057%

    No Known Activations