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

    Neuronpedia

    INDEX
    Explanations

    terms related to energy efficiency in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orgh
    -0.15
    rats
    -0.15
    ãĥ¡ãĥ©
    -0.14
    uttle
    -0.14
    ottage
    -0.14
    ilha
    -0.14
    amente
    -0.14
    esan
    -0.14
    oulos
    -0.14
    deme
    -0.13
    POSITIVE LOGITS
     compress
    0.39
    compress
    0.35
     compressor
    0.34
     compression
    0.30
     compressed
    0.29
    .compress
    0.28
     cond
    0.28
    compression
    0.27
     refriger
    0.26
    _compress
    0.26
    Act Density 0.018%

    No Known Activations