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

    Neuronpedia

    INDEX
    Explanations

    references to the United Nations (U.N.)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the United Nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geral
    -0.75
    abouts
    -0.73
    EStream
    -0.68
     lengths
    -0.68
     Lovecraft
    -0.65
     skate
    -0.62
     shave
    -0.62
     Manit
    -0.61
     coh
    -0.61
     puff
    -0.61
    POSITIVE LOGITS
    istani
    0.98
     ambassador
    0.83
    emic
    0.83
    ationally
    0.79
    orean
    0.79
    ATIONAL
    0.78
    ominated
    0.78
    SC
    0.75
     Security
    0.75
    igel
    0.73
    Act Density 0.007%

    No Known Activations