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

    Neuronpedia

    INDEX
    Explanations

    references to locations or incidents involving military engagements or injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.48
     Brésil
    -0.47
    <?
    -0.46
    ETIES
    -0.46
     Eich
    -0.45
    лык
    -0.45
    σθαι
    -0.44
     Brasil
    -0.43
    ukasz
    -0.43
     cappuccio
    -0.43
    POSITIVE LOGITS
     Afghanistan
    1.57
     Afghan
    1.52
     Taliban
    1.45
     Kabul
    1.42
    Afghanistan
    1.39
    Afghan
    1.35
     afghan
    1.30
     Afghans
    1.26
     Afgan
    1.20
    ABUL
    1.05
    Act Density 0.092%

    No Known Activations