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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to proportions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     RSSSF
    -0.60
    akhstan
    -0.57
    declar
    -0.54
    eseorang
    -0.54
     secondaires
    -0.52
    shafen
    -0.52
    Declar
    -0.52
     meubles
    -0.51
    
    -0.51
    verlag
    -0.50
    POSITIVE LOGITS
    StructEnd
    0.91
     every
    0.66
    WebServlet
    0.65
     Rood
    0.63
    ImageContext
    0.62
     RouterModule
    0.61
    zeera
    0.60
    every
    0.58
    TextHelper
    0.57
    ंदीखरीदारी
    0.56
    Act Density 0.010%

    No Known Activations