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

    Neuronpedia

    INDEX
    Explanations

    instances of people's names and their associated actions or roles in violent contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hentet
    -0.71
    zheimer
    -0.61
    urlpatterns
    -0.60
    Pratique
    -0.54
    addCriterion
    -0.53
    ibrated
    -0.53
     OMITBAD
    -0.52
     <=",
    -0.52
    StoryboardSegue
    -0.52
    FormTagHelper
    -0.52
    POSITIVE LOGITS
     victim
    0.68
    被害
    0.62
     victims
    0.60
     unprotected
    0.58
     víctima
    0.56
     attacked
    0.55
     vítima
    0.55
    Ouch
    0.55
     Opfer
    0.54
    victim
    0.54
    Act Density 0.395%

    No Known Activations