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

    Neuronpedia

    INDEX
    Explanations

    mentions of government actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to diplomatic activities or concerns involving government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Slayer
    -0.82
    ãĤ¦ãĤ¹
    -0.80
    surv
    -0.79
    killer
    -0.79
    à¼
    -0.76
     arcade
    -0.74
    Pred
    -0.74
     Linear
    -0.73
    Measure
    -0.73
     creek
    -0.73
    POSITIVE LOGITS
     diplomats
    1.87
     embassies
    1.76
     diplomatic
    1.74
     embassy
    1.70
     consulate
    1.49
     Ambassador
    1.48
     diplomat
    1.47
     ambassadors
    1.47
     Tillerson
    1.47
     Embassy
    1.46
    Act Density 0.790%

    No Known Activations