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

    Neuronpedia

    INDEX
    Explanations

    concepts related to international relations and diplomatic efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interval
    -0.15
    imax
    -0.14
     def
    -0.14
     Hiro
    -0.13
    dist
    -0.13
    NAL
    -0.13
     Lobby
    -0.13
     Pavel
    -0.13
    ETA
    -0.13
     Wright
    -0.13
    POSITIVE LOGITS
     Belt
    0.43
     Silk
    0.35
     belt
    0.31
    belt
    0.30
     silk
    0.26
     OB
    0.25
     belts
    0.23
     Infrastructure
    0.23
    OB
    0.20
    ä¸Ŀ
    0.19
    Act Density 0.069%

    No Known Activations