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

    Neuronpedia

    INDEX
    Explanations

    text related to political events, conflicts, and attacks in specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to violent or aggressive actions in geopolitical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     someday
    -0.95
     glim
    -0.84
     zoning
    -0.83
     bumps
    -0.75
    aukee
    -0.75
     renov
    -0.73
     upstairs
    -0.73
     apprentices
    -0.72
     downtown
    -0.71
     remod
    -0.70
    POSITIVE LOGITS
    Statement
    1.11
    AFP
    1.10
    BBC
    1.04
    Russia
    0.97
    Moscow
    0.97
    Terror
    0.96
     Whilst
    0.96
     Wikileaks
    0.95
    Reuters
    0.94
     Retrieved
    0.94
    Act Density 0.704%

    No Known Activations