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

    Neuronpedia

    INDEX
    Explanations

    references to embassies and diplomatic activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SKU
    -0.51
    stdafx
    -0.51
     boards
    -0.51
    WaitGroup
    -0.51
    Lynx
    -0.50
    БК
    -0.50
    atschapp
    -0.49
    npos
    -0.49
    ẵn
    -0.49
     skyl
    -0.48
    POSITIVE LOGITS
     embassies
    0.92
     embassy
    0.91
     Diplomatic
    0.89
     diplomatic
    0.89
     ambassade
    0.84
     diplomats
    0.84
     Ambassador
    0.83
     ambassadors
    0.83
     Embassy
    0.81
     ambassador
    0.81
    Act Density 0.139%

    No Known Activations