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

    Neuronpedia

    INDEX
    Explanations

    terms related to freedom or absence of certain restrictions

    oai_token-act-pair · gpt-3.5-turbo

    the concept of being 'free' from restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    older
    -0.73
    ional
    -0.68
    emet
    -0.66
    IRD
    -0.66
    asin
    -0.65
    UAL
    -0.65
    quickShipAvailable
    -0.65
    illac
    -0.64
    bourg
    -0.64
    args
    -0.64
    POSITIVE LOGITS
    zing
    1.32
    bies
    1.25
    zes
    1.15
    ze
    1.08
    zers
    1.01
    zed
    0.99
    zer
    0.90
     zones
    0.86
    ZE
    0.85
    bie
    0.83
    Act Density 0.025%

    No Known Activations