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

    Neuronpedia

    INDEX
    Explanations

    words related to political or diplomatic contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the United Nations Security Council

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.79
    yond
    -0.76
    amaz
    -0.74
    ICA
    -0.73
    days
    -0.70
    icular
    -0.70
    cause
    -0.70
    ting
    -0.69
    hes
    -0.68
    ICAN
    -0.67
    POSITIVE LOGITS
     Advisor
    1.13
     Adviser
    1.10
     Advis
    0.99
     Agency
    0.97
     Forces
    0.96
     Analyst
    0.95
     Patrol
    0.91
     Policy
    0.91
     Assistance
    0.90
     Cooperation
    0.88
    Act Density 0.020%

    No Known Activations