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

    Neuronpedia

    INDEX
    Explanations

    references to military actions and geopolitics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tron
    -0.16
    erguson
    -0.15
     Ebola
    -0.15
     dumped
    -0.15
    antium
    -0.14
    iler
    -0.14
    wich
    -0.14
     Cair
    -0.14
    絡
    -0.14
    UpDown
    -0.14
    POSITIVE LOGITS
     Ukraine
    0.35
     Ukrain
    0.35
     Ukrainian
    0.34
     Ky
    0.33
     Ukr
    0.29
     ky
    0.28
     Biden
    0.27
     Uk
    0.26
     Putin
    0.26
    Ky
    0.26
    Act Density 0.043%

    No Known Activations