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

    Neuronpedia

    INDEX
    Explanations

    copyright information in text

    oai_token-act-pair · gpt-3.5-turbo

    references to copyright and intellectual property rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.65
    thening
    -0.61
    aneously
    -0.59
    glers
    -0.58
    aturdays
    -0.57
     beds
    -0.56
    agger
    -0.55
    trap
    -0.55
    gling
    -0.55
    rique
    -0.54
    POSITIVE LOGITS
     reserved
    1.44
     Reserved
    1.35
     belong
    0.86
     permissions
    0.80
     granted
    0.77
     unavailable
    0.71
     belonged
    0.70
     Used
    0.67
     permission
    0.67
     belongs
    0.65
    Act Density 0.017%

    No Known Activations