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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal permissions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulative
    -0.78
    arer
    -0.72
    sonian
    -0.71
    nces
    -0.70
    oche
    -0.69
    vae
    -0.66
    famous
    -0.63
    enegger
    -0.61
    ilde
    -0.61
     Lans
    -0.61
    POSITIVE LOGITS
     permission
    1.11
     permissions
    0.91
    Reviewer
    0.86
     slips
    0.80
     clearance
    0.80
     waivers
    0.78
     granted
    0.77
    ittee
    0.77
    ibl
    0.76
     consent
    0.75
    Act Density 0.016%

    No Known Activations