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

    Neuronpedia

    INDEX
    Explanations

    initials with capital U in association with a following name or title

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'U' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Noir
    -0.88
    ãĤ©
    -0.72
     Preferred
    -0.72
     Syndicate
    -0.70
     CDs
    -0.66
     Solitaire
    -0.66
     Respons
    -0.66
     blinded
    -0.65
     Siren
    -0.65
     Pioneer
    -0.65
    POSITIVE LOGITS
    isine
    1.04
    nexpected
    1.03
    seless
    1.03
    PDATED
    1.00
    NA
    1.00
    prising
    0.99
    CLA
    0.99
    raviolet
    0.98
    berman
    0.95
    pper
    0.94
    Act Density 0.020%

    No Known Activations