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

    Neuronpedia

    INDEX
    Explanations

    names of actors and actresses

    oai_token-act-pair · gpt-3.5-turbo

    references to actors and their roles in films or television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caches
    -0.82
    sterdam
    -0.77
    osate
    -0.77
    à¼
    -0.76
    Statistics
    -0.74
    Economic
    -0.71
    OTAL
    -0.71
     routers
    -0.71
    FAQ
    -0.71
     deflation
    -0.70
    POSITIVE LOGITS
     audition
    1.62
     actor
    1.62
     actresses
    1.59
     actress
    1.55
     cameo
    1.54
     actors
    1.52
    Actor
    1.42
     casting
    1.41
     roles
    1.36
     Actor
    1.35
    Act Density 0.544%

    No Known Activations