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

    Neuronpedia

    INDEX
    Explanations

    details of violent incidents or attacks

    oai_token-act-pair · gpt-3.5-turbo

    instances of violent actions followed by a perpetrator

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iture
    -0.80
    utical
    -0.79
    imei
    -0.77
    estine
    -0.76
    enth
    -0.75
    tions
    -0.75
    Finish
    -0.74
    othe
    -0.74
    pring
    -0.73
    Favorite
    -0.73
    POSITIVE LOGITS
     gunmen
    1.15
     thugs
    1.13
     gunfire
    1.11
     robbers
    1.08
     bandits
    1.06
     unidentified
    1.03
     mobs
    1.01
     assailants
    1.00
     snipers
    0.96
     assassins
    0.95
    Act Density 0.152%

    No Known Activations