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

    Neuronpedia

    INDEX
    Explanations

    content related to violence, crime, and social unrest

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence and oppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     congr
    -0.74
     Tycoon
    -0.69
    ernaut
    -0.67
    ellation
    -0.66
     proponent
    -0.64
    ultimate
    -0.64
    framework
    -0.61
     Ranking
    -0.61
    inventoryQuantity
    -0.61
     nutshell
    -0.60
    POSITIVE LOGITS
     balcon
    1.03
     indiscrim
    0.95
     roofs
    0.86
     sidewalks
    0.85
     carts
    0.84
     etc
    0.83
     detainees
    0.83
     throats
    0.79
     passers
    0.79
     kitchens
    0.77
    Act Density 0.503%

    No Known Activations