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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal activities and accidents

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving violence and crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isSpecialOrderable
    -0.78
    nai
    -0.77
    DragonMagazine
    -0.76
    eworld
    -0.75
    女
    -0.72
     horm
    -0.70
     Centauri
    -0.70
    Age
    -0.70
    channelAvailability
    -0.69
     Profession
    -0.68
    POSITIVE LOGITS
     burglary
    0.98
     gunfire
    0.90
     burgl
    0.88
     gunshots
    0.87
     police
    0.84
     deton
    0.83
     LAPD
    0.82
     detonated
    0.81
     bursts
    0.80
    police
    0.79
    Act Density 0.417%

    No Known Activations