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

    Neuronpedia

    INDEX
    Explanations

    commands or lines of code written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and commands related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hordes
    -0.51
     bathrooms
    -0.49
     UFOs
    -0.48
     toilets
    -0.48
     wipes
    -0.47
     corpses
    -0.47
     cures
    -0.44
     billions
    -0.44
     houses
    -0.44
     lasers
    -0.44
    POSITIVE LOGITS
    artisan
    0.54
    amic
    0.48
    utter
    0.48
    ĺ
    0.48
    amb
    0.47
    attr
    0.46
    uted
    0.46
    ason
    0.46
    arter
    0.45
    ciplinary
    0.45
    Act Density 1.204%

    No Known Activations