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

    Neuronpedia

    INDEX
    Explanations

    terms related to empty data structures and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.52
     ContentValues
    -0.43
    ########.
    -0.43
     demand
    -0.42
    èdent
    -0.42
    NUMX
    -0.41
     Clever
    -0.40
    rupulous
    -0.40
    astéroïdes
    -0.39
    #+#
    -0.39
    POSITIVE LOGITS
     mijne
    0.54
     amitié
    0.50
    AutoScaleMode
    0.48
     tempio
    0.47
     amizade
    0.46
     désert
    0.45
     leeftijd
    0.45
     voisins
    0.45
     pís
    0.45
     Infór
    0.44
    Act Density 1.053%

    No Known Activations