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

    Neuronpedia

    INDEX
    Explanations

    references to privileges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.42
     psicología
    -0.41
     omge
    -0.41
     coches
    -0.40
     policías
    -0.39
     ciudadana
    -0.39
     fronteras
    -0.39
     Naciones
    -0.38
     bomberos
    -0.38
     kepercayaan
    -0.38
    POSITIVE LOGITS
     resourceCulture
    1.02
     privileges
    1.02
     Privile
    1.01
     queſta
    1.00
    privile
    1.00
    <unused3>
    1.00
    [@BOS@]
    1.00
    <unused28>
    0.99
    <unused14>
    0.99
    <unused8>
    0.99
    Act Density 0.188%

    No Known Activations