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

    Neuronpedia

    INDEX
    Explanations

    references to military actions and territorial control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Czech
    -0.45
     
    -0.41
     data
    -0.39
    ↵↵
    -0.38
     اسرائ
    -0.37
     italiano
    -0.37
     opérateur
    -0.37
     scri
    -0.37
     \
    -0.36
     Sopho
    -0.36
    POSITIVE LOGITS
     conquest
    0.98
     Paglinawan
    0.94
     conquering
    0.93
     conquered
    0.93
     victorious
    0.89
     alliances
    0.89
     rebellion
    0.88
     defeated
    0.87
     conquests
    0.87
     victories
    0.86
    Act Density 0.755%

    No Known Activations