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

    Neuronpedia

    INDEX
    Explanations

    content related to voluntary actions or agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voluntary actions and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.83
    marks
    -0.80
    osite
    -0.77
    mers
    -0.75
    nings
    -0.73
    geist
    -0.73
    mill
    -0.73
    emark
    -0.73
    GPU
    -0.72
    raph
    -0.72
    POSITIVE LOGITS
    untarily
    1.09
     manslaughter
    1.06
    untary
    1.02
     surrender
    1.01
     voluntary
    0.93
    unte
    0.93
     relinqu
    0.88
     enlist
    0.86
     involuntary
    0.83
     euth
    0.82
    Act Density 0.022%

    No Known Activations