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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aison
    -0.15
     bitwise
    -0.15
    ooth
    -0.15
    ãĥĥãĥĦ
    -0.15
    å¿Ļ
    -0.15
    idae
    -0.14
    iaux
    -0.14
     FUNCTIONS
    -0.14
     Functions
    -0.14
    utan
    -0.14
    POSITIVE LOGITS
     shape
    0.32
     dimensions
    0.31
     dimension
    0.30
    shape
    0.29
     Dimensions
    0.28
     batch
    0.28
     Shape
    0.27
    Shape
    0.26
    batch
    0.25
     Batch
    0.25
    Act Density 0.030%

    No Known Activations