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

    Neuronpedia

    INDEX
    Explanations

    code structures and data types in programming-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emat
    -0.16
    indsight
    -0.16
    imson
    -0.16
    762
    -0.16
    rada
    -0.15
    bara
    -0.15
     kho
    -0.15
    æ®
    -0.15
    stroy
    -0.14
     McDon
    -0.14
    POSITIVE LOGITS
     size
    0.40
    size
    0.30
    -size
    0.28
    	size
    0.27
     sizes
    0.27
    .size
    0.26
     unsigned
    0.26
    (size
    0.26
     Size
    0.25
     sized
    0.24
    Act Density 0.054%

    No Known Activations