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

    Neuronpedia

    INDEX
    Explanations

    references to different areas, such as cities, states, countries, and the world in general, as well as certain specific names and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent journalists and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bruising
    -0.66
     sim
    -0.57
     cooldown
    -0.56
     fres
    -0.55
     nighttime
    -0.54
     results
    -0.54
    advertisement
    -0.54
     wrinkles
    -0.53
    flation
    -0.53
    holiday
    -0.52
    POSITIVE LOGITS
     deserve
    1.49
     agree
    1.23
     intend
    1.21
     realize
    1.18
     want
    1.18
     know
    1.17
     recognize
    1.17
     understand
    1.16
     despise
    1.16
     owe
    1.14
    Act Density 0.526%

    No Known Activations