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

    Neuronpedia

    INDEX
    Explanations

    phrases related to seeking or granting permission

    oai_token-act-pair · gpt-3.5-turbo

    references to obtaining or granting permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulative
    -0.72
     Revel
    -0.71
    itched
    -0.68
    ilde
    -0.68
    ulz
    -0.68
    sonian
    -0.67
    oche
    -0.65
    arer
    -0.65
    enegger
    -0.63
    famous
    -0.62
    POSITIVE LOGITS
     permission
    1.14
     permissions
    0.98
    Reviewer
    0.84
     waivers
    0.83
     granted
    0.83
     clearance
    0.82
     slips
    0.82
    ibl
    0.76
     authorizing
    0.75
     decree
    0.74
    Act Density 0.019%

    No Known Activations