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

    Neuronpedia

    INDEX
    Explanations

    references to military and geopolitical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    201
    -0.18
    çİĦ
    -0.16
    boro
    -0.16
    LEM
    -0.15
     ryb
    -0.15
    andle
    -0.15
    976
    -0.15
    ãĥ³ãĤ¬
    -0.14
     Melania
    -0.14
    barang
    -0.14
    POSITIVE LOGITS
     Saddam
    0.36
     Iraq
    0.36
     Iraqi
    0.35
     Baghdad
    0.32
    Iraq
    0.30
     Coalition
    0.30
     Sadd
    0.29
     coalition
    0.28
     Ba
    0.28
     Hussein
    0.27
    Act Density 0.030%

    No Known Activations