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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to software bug fixes or enhancements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to software updates and bug fixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -1.13
    llah
    -0.84
    ¯
    -0.80
    hander
    -0.80
    arious
    -0.77
    é¾įåĸļ士
    -0.77
    chool
    -0.73
    tnc
    -0.72
    writers
    -0.72
    imilar
    -0.72
    POSITIVE LOGITS
     Fixes
    0.86
     typo
    0.68
     wording
    0.65
     Runtime
    0.64
     workaround
    0.64
     Commentary
    0.64
     experimental
    0.61
     canonical
    0.61
     Flor
    0.60
     FG
    0.60
    Act Density 0.069%

    No Known Activations