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

    Neuronpedia

    INDEX
    Explanations

    specific references to the United Nations (U.N.)

    oai_token-act-pair · gpt-3.5-turbo

    references to the United Nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lengths
    -0.72
     Manit
    -0.72
     skate
    -0.70
    ebook
    -0.70
    abouts
    -0.69
     puff
    -0.69
     Geral
    -0.67
     Lovecraft
    -0.66
     shave
    -0.66
    kson
    -0.65
    POSITIVE LOGITS
    CLASSIFIED
    0.91
    istani
    0.86
    ICE
    0.85
    ITED
    0.82
     ambassador
    0.81
    ISA
    0.81
    ominated
    0.79
     Security
    0.79
    ATIONAL
    0.79
    ZI
    0.77
    Act Density 0.013%

    No Known Activations