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

    Neuronpedia

    INDEX
    Explanations

    different instances of the phrase "built-in"

    oai_token-act-pair · gpt-3.5-turbo

    references to built-in features or components of devices or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pupp
    -0.65
     Toll
    -0.63
    Ĥª
    -0.60
     Mond
    -0.59
     Straw
    -0.59
     Unsure
    -0.58
     Visitors
    -0.57
     Centauri
    -0.57
     Kenn
    -0.56
     Parables
    -0.56
    POSITIVE LOGITS
    ins
    0.96
    in
    0.90
    fledged
    0.89
    INS
    0.86
    essential
    0.80
    scope
    0.77
    onite
    0.76
    library
    0.74
    environment
    0.72
    eatured
    0.70
    Act Density 0.031%

    No Known Activations