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

    Neuronpedia

    INDEX
    Explanations

    references to things being built or constructed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "built" and its variations, indicating a focus on construction or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ette
    -0.65
     McGill
    -0.62
     contag
    -0.61
     fever
    -0.61
     needle
    -0.60
     Agency
    -0.60
     vice
    -0.59
     halftime
    -0.59
     whistleblowers
    -0.59
     dear
    -0.58
    POSITIVE LOGITS
    built
    4.12
    Built
    2.20
    designed
    1.81
    build
    1.73
     Built
    1.71
    made
    1.58
     built
    1.52
    Constructed
    1.36
    developed
    1.34
    installed
    1.33
    Act Density 0.023%

    No Known Activations