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

    Neuronpedia

    INDEX
    Explanations

    actions and events related to crime and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assen
    -0.15
    solete
    -0.15
    888
    -0.15
    orman
    -0.15
    apa
    -0.14
    isson
    -0.14
    çIJ´
    -0.14
    ledon
    -0.14
    655
    -0.14
    ardware
    -0.14
    POSITIVE LOGITS
     unknown
    0.22
     suspected
    0.19
     dark
    0.18
     male
    0.18
     female
    0.17
     suspects
    0.17
     approximately
    0.17
    unknown
    0.17
     suspect
    0.17
     suspicious
    0.17
    Act Density 0.075%

    No Known Activations