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

    Neuronpedia

    INDEX
    Explanations

    terms related to violent crime and its aftermath

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.51
    limia
    -0.51
     kasarigan
    -0.51
    -0.50
    IntoConstraints
    -0.49
    anskrit
    -0.47
    ronpa
    -0.47
    illoma
    -0.46
     yoda
    -0.46
     Chwiliwch
    -0.45
    POSITIVE LOGITS
     bullets
    0.53
     bullet
    0.51
     gunfire
    0.49
     herido
    0.49
     wounds
    0.44
     herida
    0.44
     stabbed
    0.44
     guns
    0.43
    bullets
    0.43
     gunshot
    0.43
    Act Density 0.258%

    No Known Activations