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

    Neuronpedia

    INDEX
    Explanations

    references to memory addresses in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     z
    -0.60
     effect
    -0.56
     de
    -0.54
     Dist
    -0.53
     has
    -0.53
     &
    -0.53
     se
    -0.52
     he
    -0.51
     Fac
    -0.50
     Co
    -0.50
    POSITIVE LOGITS
     Monfieur
    0.99
     religieuses
    0.99
     étrangères
    0.93
     AssemblyProduct
    0.90
     étrangère
    0.88
     iſt
    0.87
     $_"
    0.86
    antaranya
    0.84
     Theſe
    0.84
     Anſ
    0.83
    Act Density 0.138%

    No Known Activations