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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violent actions or incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents and statistics related to crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -1.02
    ledge
    -0.80
    affer
    -0.77
    ãĤ¨
    -0.75
    ractive
    -0.72
    AH
    -0.71
    ategic
    -0.70
    Position
    -0.70
    ETF
    -0.70
    DIS
    -0.69
    POSITIVE LOGITS
     northeastern
    0.94
     cities
    0.89
     robberies
    0.87
     Northeast
    0.87
     southeastern
    0.86
     mosques
    0.86
     southern
    0.85
     northwestern
    0.84
     southwestern
    0.84
     downtown
    0.84
    Act Density 0.228%

    No Known Activations