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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to the United Nations or its various entities

    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
    -0.99
    rolet
    -0.80
    ebook
    -0.78
    idious
    -0.68
    Bloom
    -0.62
    abouts
    -0.62
    ãħĭãħĭ
    -0.61
    esian
    -0.60
    wagen
    -0.59
    akespeare
    -0.59
    POSITIVE LOGITS
     intervene
    0.81
     Intervention
    0.76
     Security
    0.75
    itory
    0.74
     Ambassador
    0.70
    psey
    0.70
     Headquarters
    0.69
     inspectors
    0.68
     Assistance
    0.68
     Refugee
    0.68
    Act Density 0.028%

    No Known Activations