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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing crises or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    events related to conflicts and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.89
     Libraries
    -0.87
     Editors
    -0.84
    natureconservancy
    -0.81
     desks
    -0.78
     cabinets
    -0.76
    thood
    -0.75
    Reading
    -0.75
     scrolls
    -0.74
     hats
    -0.74
    POSITIVE LOGITS
     perpetrated
    1.21
     inflicted
    1.07
     aggravated
    1.01
     plag
    1.01
     caused
    0.98
     exacerbated
    0.97
     rav
    0.94
     metast
    0.92
     engulf
    0.90
     occurring
    0.90
    Act Density 0.725%

    No Known Activations