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

    Neuronpedia

    INDEX
    Explanations

    references to empirical studies or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fromnode
    -0.50
     propOrder
    -0.50
     Christus
    -0.48
    AISSEE
    -0.44
     Numerade
    -0.43
     dön
    -0.43
    ształ
    -0.42
    guisement
    -0.41
    heritance
    -0.41
     gloire
    -0.40
    POSITIVE LOGITS
     Sierra
    0.50
    Sierra
    0.49
     hack
    0.47
     empirical
    0.44
     esternos
    0.42
    Rüyada
    0.42
     skins
    0.42
     nominal
    0.42
     vulgares
    0.42
    attrs
    0.41
    Act Density 1.700%

    No Known Activations