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

    Neuronpedia

    INDEX
    Explanations

    references to a specific location named "Donetsk"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city Donetsk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Russell
    -0.81
    Adapt
    -0.78
    ZX
    -0.76
    ISON
    -0.76
    xon
    -0.76
    ober
    -0.74
    Label
    -0.72
    Mach
    -0.72
    ASED
    -0.72
    reviewed
    -0.72
    POSITIVE LOGITS
     Donetsk
    1.19
     Ukraine
    0.96
    etsk
    0.94
    ansk
    0.94
     Crimea
    0.82
     Ukrain
    0.80
     Ukrainian
    0.80
     Kiev
    0.80
    ovsky
    0.79
     Lumpur
    0.74
    Act Density 0.015%

    No Known Activations