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

    Neuronpedia

    INDEX
    Explanations

    references to scientific figures and citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     cristian
    -0.50
    мені
    -0.49
     matrimon
    -0.49
     finition
    -0.46
     cristi
    -0.46
    -0.46
    ricular
    -0.45
    LHS
    -0.45
    amental
    -0.45
     nasional
    -0.45
    POSITIVE LOGITS
    
    1.03
     متعلقه
    0.97
    sizeCache
    0.90
    !*\
    0.86
    AccessorTable
    0.86
    fjspx
    0.84
    AddTagHelper
    0.83
    awtextra
    0.82
     defaultstate
    0.81
    UnusedPrivate
    0.80
    Act Density 0.001%

    No Known Activations