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

    Neuronpedia

    INDEX
    Explanations

    terms related to whistleblower protections and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apus
    -0.16
     Taste
    -0.16
    mins
    -0.14
    绣
    -0.14
     MILF
    -0.14
    ÙĨÚ¯ÛĮ
    -0.14
    ÙĦÛĮسÛĮ
    -0.14
    .GetEnumerator
    -0.13
    jer
    -0.13
    /epl
    -0.13
    POSITIVE LOGITS
     whistleblower
    0.33
     whistlebl
    0.31
     whistle
    0.31
     anonymous
    0.26
     blowing
    0.26
     Protected
    0.23
     protected
    0.23
    anonymous
    0.23
     Anonymous
    0.23
     blow
    0.23
    Act Density 0.011%

    No Known Activations