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

    Neuronpedia

    INDEX
    Explanations

    references to illegal activities and drug-related crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the neuron detects words and phrases about illegal drugs, drug trafficking, and related organized-crime activity.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Negative Logits
     fédé
    -0.71
    Diweddarwch
    -0.69
     présidenti
    -0.64
     chré
    -0.62
     الحره
    -0.61
     heureuse
    -0.61
     holotype
    -0.60
     complètes
    -0.59
     vectoriales
    -0.59
     ivelany
    -0.59
    POSITIVE LOGITS
     illegal
    0.95
    illegal
    0.75
     illegally
    0.73
     Illegal
    0.72
    Illegal
    0.70
     illicit
    0.69
     street
    0.59
     ilegal
    0.58
     clandestine
    0.58
     unregulated
    0.58
    Act Density 0.364%

    No Known Activations