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

    Neuronpedia

    INDEX
    Explanations

    keywords related to whistleblowing or blowing the whistle on a situation

    oai_token-act-pair · gpt-3.5-turbo

    references to whistleblowers and the act of blowing whistles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seq
    -0.75
    Urban
    -0.73
    Ļ½
    -0.73
    yrinth
    -0.73
    rators
    -0.72
     Expend
    -0.68
     resid
    -0.68
    ivia
    -0.67
    Interstitial
    -0.65
    izable
    -0.64
    POSITIVE LOGITS
    dropping
    1.06
     whistle
    1.06
    pipe
    0.90
    keeper
    0.90
     whist
    0.88
     blowing
    0.84
     tip
    0.80
     sounded
    0.78
    leading
    0.78
    keepers
    0.77
    Act Density 0.061%

    No Known Activations