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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to whistleblower protections and laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alim
    -0.17
    adium
    -0.16
    emo
    -0.15
    tah
    -0.15
    _fwd
    -0.14
    ras
    -0.14
    ighet
    -0.14
    enso
    -0.14
    ports
    -0.13
    strand
    -0.13
    POSITIVE LOGITS
     protected
    0.19
    .gf
    0.17
     Protected
    0.17
     protection
    0.16
    protected
    0.16
     employee
    0.15
     Employee
    0.14
     Pentagon
    0.14
    ajas
    0.14
     fil
    0.14
    Act Density 0.045%

    No Known Activations