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

    Neuronpedia

    INDEX
    Explanations

    words related to authorization and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    authorize and its forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __((
    -0.44
     esattamente
    -0.42
     Unser
    -0.42
    mentazione
    -0.40
     égard
    -0.40
     inoxydable
    -0.38
     fondamentali
    -0.38
    Аб
    -0.37
     Properly
    -0.37
     semplici
    -0.37
    POSITIVE LOGITS
    authorize
    2.86
    Authorize
    2.14
     authorize
    1.92
     authorizing
    1.25
     authorizes
    1.22
    authorized
    1.03
     authorized
    0.91
     authorization
    0.90
    Authorization
    0.89
     Authorization
    0.84
    Act Density 0.002%

    No Known Activations