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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal regulations and restrictions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal regulations and statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wow
    -0.84
     Lauder
    -0.75
    nir
    -0.73
    DragonMagazine
    -0.72
     Jagu
    -0.71
    uture
    -0.71
    terday
    -0.70
    Pak
    -0.70
    ï¸ı
    -0.70
     Wow
    -0.70
    POSITIVE LOGITS
     employers
    0.95
     nonprofits
    0.95
     willful
    0.95
     minors
    0.95
     compelled
    0.94
     discrimination
    0.92
     interference
    0.91
     unreasonable
    0.91
     "[
    0.89
     exceptions
    0.89
    Act Density 0.218%

    No Known Activations