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

    Neuronpedia

    INDEX
    Explanations

    sections or markers indicating code blocks or boundaries in programming languages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.97
     تضيفلها
    -0.94
     مشين
    -0.93
    LookAnd
    -0.90
    IsMutable
    -0.90
     الحره
    -0.90
     Numerade
    -0.88
     bezeichneter
    -0.87
    AccessorTable
    -0.87
    PerformLayout
    -0.85
    POSITIVE LOGITS
     net
    0.54
     then
    0.50
    ops
    0.50
    //
    0.47
     vise
    0.45
    chooser
    0.44
     un
    0.44
     Net
    0.44
     gri
    0.44
     ACT
    0.43
    Act Density 0.046%

    No Known Activations