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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to terrorism

    oai_token-act-pair · gpt-3.5-turbo

    references to Osama bin Laden and related political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âķIJ
    -0.72
    hips
    -0.71
    drawn
    -0.71
    flies
    -0.70
    haw
    -0.69
    maid
    -0.69
    eries
    -0.68
    hire
    -0.68
    ships
    -0.66
    yards
    -0.66
    POSITIVE LOGITS
     bin
    1.06
     Bin
    1.04
     Hussein
    0.97
     Hassan
    0.89
     rall
    0.86
     ibn
    0.84
     Osama
    0.81
     Abdullah
    0.78
    atis
    0.77
     Laden
    0.76
    Act Density 0.013%

    No Known Activations