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

    Neuronpedia

    INDEX
    Explanations

    references to violent incidents or acts of terrorism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.63
     propOrder
    -0.55
    хьтан
    -0.45
    sidemargin
    -0.45
     للمعارف
    -0.44
    OGND
    -0.44
    Autoritní
    -0.42
    InputTagHelper
    -0.41
    XmlAccessorType
    -0.41
     linkovi
    -0.40
    POSITIVE LOGITS
     incidents
    0.75
     crimes
    0.68
     incident
    0.66
     injuries
    0.64
     victims
    0.63
     threatening
    0.63
     deaths
    0.61
     injuring
    0.59
     crime
    0.58
     accidents
    0.57
    Act Density 0.348%

    No Known Activations