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

    Neuronpedia

    INDEX
    Explanations

    references to geopolitical tensions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nish
    -0.16
     Chow
    -0.15
    oma
    -0.15
    اصÙĦ
    -0.14
     Siber
    -0.14
     tofu
    -0.14
    alph
    -0.14
    ãģĤãģĴ
    -0.14
     Philosoph
    -0.13
    cec
    -0.13
    POSITIVE LOGITS
     Trump
    0.37
     Kushner
    0.35
     Bahrain
    0.30
     Jared
    0.30
    Trump
    0.29
     normalization
    0.29
     UAE
    0.28
     Jerusalem
    0.27
     Pompeo
    0.27
     Donald
    0.26
    Act Density 0.026%

    No Known Activations