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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.54
     Shutterstock
    -0.54
    ndum
    -0.50
    .:
    -0.49
    .............
    -0.49
    stery
    -0.48
     ..............
    -0.48
    advertisement
    -0.47
     rally
    -0.47
    ramid
    -0.47
    POSITIVE LOGITS
     lacks
    0.91
     hasn
    0.91
     prefers
    0.88
     wasn
    0.88
     cannot
    0.87
     succeeds
    0.86
     isn
    0.86
     tends
    0.86
     doesn
    0.85
     could
    0.85
    Act Density 0.629%

    No Known Activations