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

    Neuronpedia

    INDEX
    Explanations

    mentions of geographical locations, particularly Russian cities and regions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures or entities associated with governance and regional issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ellison
    -0.85
    Haw
    -0.84
    Austral
    -0.77
    advertisement
    -0.77
    ayne
    -0.74
     Metatron
    -0.73
    Cook
    -0.73
    Oracle
    -0.72
     Hawaiian
    -0.71
     Carbuncle
    -0.71
    POSITIVE LOGITS
    etsk
    1.40
     Donetsk
    1.18
    ovo
    1.14
    kaya
    1.13
     Kremlin
    1.12
    ansk
    1.12
     Moscow
    1.10
     Soviets
    1.10
    sk
    1.06
     USSR
    1.04
    Act Density 0.216%

    No Known Activations