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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accuracy and reproduction of data or events

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

    accurately reproduce or reconstruct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.57
    RegressionTest
    -0.56
     resourceCulture
    -0.56
     jScrollPane
    -0.56
    Counters
    -0.52
    audiovisuel
    -0.52
     الحره
    -0.52
     contextLoads
    -0.51
    MethodManager
    -0.50
    berdayakan
    -0.50
    POSITIVE LOGITS
     accurate
    0.72
     accurately
    0.66
    accurate
    0.63
     Accurate
    0.63
    Accurate
    0.62
     faithfully
    0.61
     reproduction
    0.60
     reproducing
    0.59
     accuracy
    0.58
     recreate
    0.57
    Act Density 0.130%

    No Known Activations