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

    Neuronpedia

    INDEX
    Explanations

    mentions of the 9/11 attacks and related conspiracy theories

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wine
    -0.69
     MLA
    -0.67
    cil
    -0.67
    Tile
    -0.66
     Mono
    -0.65
     Huawei
    -0.65
     DRAGON
    -0.65
    Thom
    -0.65
    aird
    -0.63
    raw
    -0.62
    POSITIVE LOGITS
     anniversary
    0.97
     mastermind
    0.83
    truth
    0.83
     devastation
    0.81
     Anniversary
    0.81
     Truth
    0.80
     bombings
    0.80
     Commission
    0.80
    Truth
    0.79
     victims
    0.79
    Act Density 0.102%

    No Known Activations