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

    Neuronpedia

    INDEX
    Explanations

    words related to authorization or authority

    oai_token-act-pair · gpt-3.5-turbo

    words related to authorization and permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enth
    -0.91
    fish
    -0.76
    mania
    -0.74
    ï¸ı
    -0.70
    mates
    -0.69
    gaard
    -0.68
    EMS
    -0.67
    bows
    -0.66
    Unity
    -0.65
    âĺħ
    -0.64
    POSITIVE LOGITS
     authorizing
    1.02
     authorization
    0.86
    ittees
    0.81
     authorized
    0.78
    authorized
    0.78
     authorize
    0.77
    ittee
    0.76
     appropriations
    0.75
     permission
    0.74
    Reviewer
    0.73
    Act Density 0.038%

    No Known Activations