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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the term "retired."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.16
    etsk
    -0.15
    ridor
    -0.15
    edException
    -0.15
    erland
    -0.15
    stead
    -0.15
    heading
    -0.15
    stru
    -0.15
    licit
    -0.15
    atten
    -0.15
    POSITIVE LOGITS
    (ret
    0.20
     ret
    0.20
     Ret
    0.19
    irement
    0.17
    iers
    0.17
    ention
    0.17
    ters
    0.16
     retina
    0.16
    -ret
    0.16
    .Ret
    0.16
    Act Density 0.026%

    No Known Activations