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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict and war

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ERT
    -0.66
     NRS
    -0.65
     Orig
    -0.64
     acc
    -0.62
     PIN
    -0.62
    ODY
    -0.62
     Hick
    -0.61
     sight
    -0.60
     Lip
    -0.60
     Rack
    -0.60
    POSITIVE LOGITS
    war
    4.29
    War
    2.29
    WAR
    2.13
     war
    1.74
     War
    1.59
    Wars
    1.42
     wars
    1.41
     WAR
    1.38
     Wars
    1.20
     warfare
    1.17
    Act Density 0.004%

    No Known Activations