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

    Neuronpedia

    INDEX
    Explanations

    words related to development and improvement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of improvements and updates related to products or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.94
     Berm
    -0.83
     Oprah
    -0.78
     Rabbi
    -0.77
     Carlson
    -0.74
     Reagan
    -0.73
    ofi
    -0.72
     Twain
    -0.71
     Hilton
    -0.70
     Costco
    -0.70
    POSITIVE LOGITS
     usability
    1.21
     update
    1.19
     SDK
    1.19
     tweaks
    1.18
     devs
    1.15
     functionality
    1.13
     optimizations
    1.11
     improvements
    1.08
     updates
    1.07
     overhaul
    1.07
    Act Density 1.050%

    No Known Activations