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

    Neuronpedia

    INDEX
    Explanations

    descriptions of software bug fixes and updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.88
    drug
    -0.80
    igion
    -0.76
     Twain
    -0.74
    enged
    -0.73
    ashington
    -0.73
     stares
    -0.72
     Oprah
    -0.72
    ogie
    -0.71
     Hilton
    -0.71
    POSITIVE LOGITS
     SDK
    1.44
     optimizations
    1.41
     deprecated
    1.37
     functionality
    1.36
     usability
    1.33
     compatibility
    1.29
     plugin
    1.28
    Version
    1.27
     implementations
    1.27
     ported
    1.27
    Act Density 5.223%

    No Known Activations