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

    Neuronpedia

    INDEX
    Explanations

    references to armed conflict, militant groups, and military operations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oard
    -0.73
     Edison
    -0.72
     Hearth
    -0.72
    hetti
    -0.69
    wyn
    -0.67
     Patent
    -0.67
     Dent
    -0.67
     Eck
    -0.66
    icka
    -0.66
     UID
    -0.65
    POSITIVE LOGITS
     militants
    1.32
     fighters
    1.15
     terrorists
    1.11
     insurgents
    1.10
     gunmen
    1.05
     jihadists
    1.03
     militant
    1.03
     insurgency
    1.02
     extremists
    1.01
     operatives
    0.95
    Act Density 0.042%

    No Known Activations