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

    Neuronpedia

    INDEX
    Explanations

    references to significant events or conspiracies involving the September 11 attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.02
    2:0.20
    3:0.07
    4:0.02
    5:0.07
    6:0.02
    7:0.07
    8:0.29
    9:0.04
    10:0.02
    11:0.02
    Negative Logits
     MLA
    -3.23
    onga
    -3.22
     Nadu
    -3.16
     Grimes
    -3.10
    xual
    -3.10
    Tenn
    -3.04
    acia
    -3.01
     DRAG
    -2.96
    gars
    -2.93
     Wilde
    -2.92
    POSITIVE LOGITS
     WTC
    5.71
     Osama
    4.93
     hij
    4.57
     hijacked
    4.47
     FEMA
    4.47
    911
    4.39
     airplanes
    4.21
     JFK
    4.13
     counterterrorism
    4.12
     terrorists
    4.10
    Act Density 0.105%

    No Known Activations