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

    Neuronpedia

    INDEX
    Explanations

    specific mention of the term "Voluntary" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Vol" along with its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sunder
    -0.67
     Rampage
    -0.67
     NIC
    -0.66
     MacArthur
    -0.66
     Annotations
    -0.63
    merce
    -0.62
     Infrastructure
    -0.61
     Clarkson
    -0.61
     Elven
    -0.61
     Synd
    -0.60
    POSITIVE LOGITS
    atile
    1.56
    untary
    1.49
    atility
    1.46
    umes
    1.34
    untarily
    1.22
    unte
    1.22
    leys
    1.06
    cano
    1.06
    UME
    1.00
    upt
    0.98
    Act Density 0.034%

    No Known Activations