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

    Neuronpedia

    INDEX
    Explanations

    terms related to efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    efficient methods and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pardo
    -0.46
    Slf
    -0.46
    StringCopy
    -0.45
     Roskov
    -0.45
     ujednoznacz
    -0.45
    daß
    -0.44
     kasarigan
    -0.44
    amiya
    -0.44
     something
    -0.44
     Danza
    -0.44
    POSITIVE LOGITS
    Efficient
    1.84
     Efficient
    1.82
     efficient
    1.77
    efficient
    1.70
     efficiently
    1.35
     eficiente
    1.26
     eficientes
    1.24
    fficient
    1.23
     effici
    1.11
     inefficient
    1.02
    Act Density 0.009%

    No Known Activations