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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific location, specifically the city of Donetsk

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Donetsk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.86
    ISON
    -0.77
    OHN
    -0.72
    sed
    -0.72
    ORED
    -0.69
    ASED
    -0.69
    HAHAHAHA
    -0.69
    Reilly
    -0.68
    rition
    -0.68
     skelet
    -0.68
    POSITIVE LOGITS
     Donetsk
    1.08
    etsk
    0.90
    ansk
    0.82
     Ukraine
    0.79
    ignty
    0.77
     Ð
    0.75
     Lumpur
    0.71
     Kiev
    0.70
    vernment
    0.70
     Memor
    0.70
    Act Density 0.027%

    No Known Activations