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

    Neuronpedia

    INDEX
    Explanations

    instances of violence and crime-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.52
    Personensuche
    -0.48
    hichever
    -0.48
     CreateTagHelper
    -0.48
     فريبيس
    -0.47
     przecież
    -0.47
     nantinya
    -0.47
    到时候
    -0.47
     zwłaszcza
    -0.45
    delà
    -0.45
    POSITIVE LOGITS
     believed
    0.77
     allegedly
    0.77
     near
    0.71
     moments
    0.69
     minutes
    0.69
     reportedly
    0.67
     hours
    0.66
     suspected
    0.65
     investigators
    0.64
     Authorities
    0.62
    Act Density 0.607%

    No Known Activations