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

    Neuronpedia

    INDEX
    Explanations

    phrases related to voluntary action or involvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voluntary actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rup
    -0.83
    nings
    -0.83
    ning
    -0.80
    ammers
    -0.79
    stable
    -0.78
    geist
    -0.77
    rums
    -0.77
    sworth
    -0.76
    osite
    -0.76
    amac
    -0.75
    POSITIVE LOGITS
     manslaughter
    1.09
     surrender
    0.99
     relinqu
    0.89
     arbitration
    0.88
     voluntary
    0.86
     induction
    0.85
     compliance
    0.84
     enlist
    0.82
     retirement
    0.81
    untary
    0.80
    Act Density 0.066%

    No Known Activations