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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "voluntary" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of voluntary actions or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.80
    marks
    -0.76
    mers
    -0.73
    mill
    -0.72
    rox
    -0.72
    raph
    -0.72
    elf
    -0.72
    udeb
    -0.71
    ondo
    -0.70
     ç¥ŀ
    -0.70
    POSITIVE LOGITS
    untarily
    1.14
    untary
    1.11
     manslaughter
    1.07
     voluntary
    1.02
    unte
    0.97
     surrender
    0.92
     relinqu
    0.87
     involuntary
    0.83
     euth
    0.83
     diseng
    0.83
    Act Density 0.015%

    No Known Activations