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

    Neuronpedia

    INDEX
    Explanations

    technical terms associated with engineering and scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lèvres
    -0.73
     épaules
    -0.68
     oreilles
    -0.64
     prêtres
    -0.63
     rigue
    -0.63
     âmes
    -0.63
     enfans
    -0.62
     bienfaits
    -0.60
     larmes
    -0.60
     pères
    -0.59
    POSITIVE LOGITS
     items
    1.20
     entities
    1.14
     pieces
    1.13
     variants
    1.05
     instances
    1.03
     units
    1.02
     cases
    1.02
     elements
    1.01
     categories
    1.01
     objects
    0.99
    Act Density 2.357%

    No Known Activations