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

    Neuronpedia

    INDEX
    Explanations

    references to the United Nations

    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
    veland
    -0.95
    oning
    -0.74
    æ³
    -0.70
    rosse
    -0.70
     sheets
    -0.67
    oak
    -0.67
    haps
    -0.65
     bits
    -0.65
    owder
    -0.63
     Lovecraft
    -0.62
    POSITIVE LOGITS
     Headquarters
    0.94
     Security
    0.90
     Ambassador
    0.89
     Framework
    0.85
     ambassador
    0.85
     diplomatic
    0.84
     Assistance
    0.84
     envoy
    0.82
     diplomats
    0.82
     Refugee
    0.80
    Act Density 0.016%

    No Known Activations