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

    Neuronpedia

    INDEX
    Explanations

    information related to violent events and conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.83
     Patent
    -0.79
     Preferences
    -0.77
     disclaimer
    -0.76
    Measure
    -0.75
     Balanced
    -0.75
    Understanding
    -0.75
     monopoly
    -0.74
    ãĤ´ãĥ³
    -0.73
    omial
    -0.72
    POSITIVE LOGITS
     injured
    1.52
     evacuated
    1.40
     wounded
    1.40
     casualties
    1.30
     victims
    1.29
     fleeing
    1.23
     killed
    1.22
     survivors
    1.21
     evac
    1.21
     fatalities
    1.21
    Act Density 2.350%

    No Known Activations